Browse State-of-the-Art › Computer Vision

Computer Vision

6,511 benchmarks 1,866 tasks 5,101 datasets 90,964 papers with code archive 2025-07-28

Syntology code harvested from 22,978 of the papers with code counted above at least one sample ran for 18,014 of them per-sample status is on each paper page

Benchmarks are leaderboard tables with at least one row whose task is in this area, counted by the task's area and not by the archive's per-table category tag, which tags 6,535 tables with Computer Vision; datasets are those the archive tags with a task in this area; papers with code are catalogue papers tagged with a task in this area that list at least one repository. Task images are not shown (the archive's image host no longer serves them).

Parent tasks

393 tasks in Computer Vision have sub-tasks in the archive's task tree, most benchmarks first, then most papers with code. Each section shows up to 5 sub-tasks; the task page lists them all.

Image Classification (33)
Semantic Segmentation (29)
Object Detection (39)
Image Generation (23)
Few-Shot Image Classification (3)
Anomaly Detection (28)
Visual Question Answering (VQA) (9)
Continuous Control (3)
Image Super-Resolution (5)
3D Object Detection (5)
Classification (24)
Domain Adaptation (13)
Semi-Supervised Image Classification (2)
Action Recognition (15)
Image Retrieval (10)
Image Clustering (4)
Medical Image Segmentation (31)
Unsupervised Domain Adaptation (1)
Sentiment Analysis (12)
Person Re-Identification (13)
Visual Place Recognition (3)
Image-to-Image Translation (11)
Instance Segmentation (17)
Fine-Grained Image Classification (1)
Continual Learning (5)
Zero-Shot Learning (7)
Image Captioning (8)
Trajectory Prediction (3)
Pose Estimation (17)
Visual Question Answering (5)
Video Question Answering (2)
Few-Shot Learning (12)
Panoptic Segmentation (2)
3D Human Pose Estimation (9)
Face Recognition (6)
Visual Object Tracking (1)
Facial Expression Recognition (FER) (5)
Novel View Synthesis (2)
Point Cloud Registration (1)
Multi-Object Tracking (6)
Referring Expression Segmentation (2)
Domain Generalization (3)
Image Denoising (2)
Face Verification (1)
2D Object Detection (15)
Video Frame Interpolation (3)
Video Retrieval (5)
3D Semantic Segmentation (5)
Video Prediction (2)
Object Localization (5)
Unsupervised Anomaly Detection (5)
Unsupervised Semantic Segmentation (1)
Text-to-Image Generation (7)
Deblurring (2)
Change Detection (1)
Action Recognition In Videos (1)
Video Generation (2)
Prompt Engineering (1)
Video Super-Resolution (1)
Semi-Supervised Video Object Segmentation (1)
Age Estimation (1)
Scene Text Recognition (1)
Depth Estimation (10)
Temporal Action Localization (8)
Video Anomaly Detection (1)
Open Vocabulary Semantic Segmentation (1)
Image Segmentation (1)
Video Object Segmentation (7)
Cross-Modal Retrieval (5)
Video Captioning (6)
Gesture Recognition (3)
Face Detection (1)
Motion Synthesis (3)
Lane Detection (1)
Few-Shot Semantic Segmentation (1)
RGB Salient Object Detection (3)
Multi-Person Pose Estimation (1)
Handwritten Text Recognition (2)
Visual Reasoning (1)
Image Inpainting (3)
Video Classification (2)
Cell Segmentation (1)
Retrieval (3)
Image Compression (4)
Action Detection (8)
Conditional Image Generation (3)
Multiple Object Tracking (2)
2D Semantic Segmentation (17)
Self-Supervised Learning (2)
Quantization (2)
Optical Flow Estimation (1)
3D Reconstruction (7)
Object Tracking (10)
Multi-Label Classification (4)
Visual Tracking (4)
Keyword Spotting (2)
Hand Pose Estimation (1)
Few-Shot Object Detection (1)
Object Counting (4)
2D Human Pose Estimation (6)
Retinal Vessel Segmentation (1)
Facial Landmark Detection (3)
Fairness (1)
Emotion Recognition (12)
Object Recognition (3)
Image Deblurring (1)
Pedestrian Detection (1)
Action Segmentation (4)
Scene Text Detection (2)
3D Face Reconstruction (1)
Cross-Domain Few-Shot (1)
3D Instance Segmentation (1)
Single-View 3D Reconstruction (1)
2D Pose Estimation (2)
Image Reconstruction (5)
DeepFake Detection (5)
Boundary Detection (1)
Image Matting (1)
No-Reference Image Quality Assessment (2)
Lipreading (1)
Human Interaction Recognition (3)
Image/Document Clustering (1)
Knowledge Distillation (2)
Image Enhancement (10)
Facial Expression Recognition (2)
Scene Graph Generation (2)
Saliency Detection (4)
Source-Free Domain Adaptation (2)
3D Hand Pose Estimation (3)
Multimodal Emotion Recognition (1)
Multi-Label Image Classification (1)
Talking Head Generation (1)
Camouflaged Object Segmentation (1)
Human action generation (1)
Denoising (6)
regression (2)
Optical Character Recognition (OCR) (10)
Class Incremental Learning (3)
Salient Object Detection (2)
Human-Object Interaction Detection (2)
Scene Segmentation (1)
Visual Navigation (1)
6D Pose Estimation (2)
Text-to-Video Generation (2)
Video Summarization (2)
Semantic correspondence (1)
Document Layout Analysis (1)
Key Information Extraction (1)
Unsupervised Panoptic Segmentation (1)
Segmentation (1)
Representation Learning (14)
Video Semantic Segmentation (1)
Image Registration (2)
Multi-class Classification (1)
3D Point Cloud Classification (4)
Scene Flow Estimation (1)
Shadow Removal (1)
Stereo Depth Estimation (1)
Visual Relationship Detection (2)
3D Multi-Person Pose Estimation (3)
Anomaly Classification (1)
Unified Image Restoration (1)
Video-Adverb Retrieval (1)
Reconstruction (4)
Autonomous Driving (6)
Meta-Learning (3)
Binary Classification (6)
Imputation (1)
Activity Recognition (11)
Visual Grounding (3)
Robot Navigation (5)
Saliency Prediction (2)
Open Vocabulary Object Detection (1)
3D Object Reconstruction (4)
Small Object Detection (1)
Point Cloud Generation (1)
3D Object Classification (2)
Dense Video Captioning (1)
3D Semantic Scene Completion (1)
Surgical phase recognition (2)
Document Text Classification (3)
Meter Reading (1)
Few-Shot Transfer Learning for Saliency Prediction (1)
Data Augmentation (2)
Style Transfer (6)
Adversarial Attack (4)
Scene Understanding (6)
Image Quality Assessment (7)
Multimodal Reasoning (1)
Point Cloud Completion (1)
Pose Tracking (1)
Zero-Shot Image Classification (1)
Image Colorization (1)
Handwriting Recognition (2)
Text to Video Retrieval (1)
Weakly-supervised Temporal Action Localization (1)
Sketch-Based Image Retrieval (1)
3D Action Recognition (6)
Multimodal Machine Translation (2)
Road Segmentation (1)
Meme Classification (1)
3D Face Animation (1)
10-shot image generation (21)
Stereo Disparity Estimation (1)
3D Anomaly Detection (2)
Continual Semantic Segmentation (2)
3D Absolute Human Pose Estimation (4)
2D Panoptic Segmentation (1)
Traffic Accident Detection (1)
Face Quality Assessement (1)
Reinforcement Learning (RL) (6)
Dimensionality Reduction (2)
Image Restoration (13)
Medical Diagnosis (5)
Colorization (3)
Rain Removal (1)
Point Cloud Classification (2)
Scene Parsing (9)
Moment Retrieval (1)
Unsupervised Image-To-Image Translation (1)
Gait Recognition (2)
3D Shape Reconstruction (1)
Human Parsing (1)
Visual Speech Recognition (1)
Video Grounding (2)
Camera Localization (2)
Shadow Detection (1)
Talking Face Generation (2)
3D Object Tracking (1)
Patch Matching (1)
Video Restoration (1)
Single-Source Domain Generalization (1)
3D Face Modelling (2)
Point Clouds (3)
Image Matching (4)
Composed Image Retrieval (CoIR) (1)
Landmark Recognition (1)
Abnormal Event Detection In Video (1)
Lung Nodule Detection (1)
Breast Cancer Histology Image Classification (2)
The Semantic Segmentation Of Remote Sensing Imagery (1)
3D Shape Reconstruction From A Single 2D Image (1)
Image Editing (5)
Unsupervised Instance Segmentation (1)
Handwriting Verification (1)
3D Point Cloud Interpolation (1)
Spoof Detection (4)
Super-Resolution (7)
Active Learning (1)
Autonomous Vehicles (15)
Instruction Following (1)
Explainable Artificial Intelligence (XAI) (1)
Video Segmentation (3)
Camera Pose Estimation (1)
Visual Odometry (2)
Motion Forecasting (2)
16k (6)
Event-based vision (3)
3D Classification (2)
Color Constancy (1)
Vision-Language Navigation (1)
Semi-supervised Anomaly Detection (2)
Content-Based Image Retrieval (2)
Dense Captioning (1)
Activity Prediction (3)
severity prediction (1)
Document AI (1)
Inverse-Tone-Mapping (1)
One-Shot Segmentation (1)
Value prediction (1)
Room Layout Estimation (1)
Audio-visual Question Answering (1)
inverse tone mapping (1)
3D Depth Estimation (1)
Activity Recognition In Videos (1)
Lung Nodule Classification (1)
Event Segmentation (1)
Human Instance Segmentation (1)
Situation Recognition (1)
Language-Based Temporal Localization (1)
Lip to Speech Synthesis (1)
Explanatory Visual Question Answering (1)
Instance Shadow Detection (1)
Single-Image-Based Hdr Reconstruction (1)
1 Image, 2*2 Stitchi (12)
Atomic action recognition (1)
Object Segmentation (3)
Period Estimation (1)
Calving Front Delineation In Synthetic Aperture Radar Imagery (1)
Fashion Understanding (1)
Multi-Oriented Scene Text Detection (1)
2D Semantic Segmentation task 3 (25 classes) (1)
Interactive 3D Instance Segmentation (1)
LMM real-life tasks (2)
Deep Learning (1)
Video Understanding (7)
Text to Image Generation (1)
Explainable artificial intelligence (3)
motion prediction (1)
Neural Rendering (1)
Autonomous Navigation (3)
Simultaneous Localization and Mapping (2)
Machine Unlearning (1)
Action Localization (4)
Face Generation (5)
document understanding (1)
Video Editing (1)
Object Reconstruction (1)
Face Reconstruction (1)
3D Scene Reconstruction (1)
Temporal Localization (2)
MULTI-VIEW LEARNING (1)
Disease Prediction (2)
Human motion prediction (1)
MRI segmentation (1)
Physics-informed machine learning (1)
Decision Making Under Uncertainty (1)
De-identification (2)
Open-Vocabulary Semantic Segmentation (1)
Indoor Localization (2)
3D Shape Representation (1)
Image to Video Generation (1)
Image Stylization (1)
Privacy Preserving Deep Learning (2)
Single Particle Analysis (1)
Iris Recognition (1)
HDR Reconstruction (1)
Human Dynamics (1)
Camera Relocalization (1)
Grasp Generation (2)
Blind Image Deblurring (1)
Fake Image Detection (2)
Class-Incremental Semantic Segmentation (12)
Segmentation Of Remote Sensing Imagery (1)
Depth And Camera Motion (1)
Diffusion Personalization (2)
3D Point Cloud Reconstruction (1)
Deception Detection (1)
Image Categorization (1)
Sketch Recognition (1)
Interest Point Detection (1)
Indoor Scene Reconstruction (1)
Instance Search (1)
Hyperspectral Image Segmentation (1)
road scene understanding (2)
1 Image, 2*2 Stitching (2)
3D Surface Generation (1)
ENF (Electric Network Frequency) Extraction (1)
Referring Multi-Object Tracking (1)
3D Shape Reconstruction from Videos (1)
Landmark Tracking (1)
Mistake Detection (1)
Fine-Grained Vehicle Classification (1)
satellite image super-resolution (1)
3D Character Animation From A Single Photo (1)
Referring Image Matting (4)
Transparent Object Detection (1)
3D Mesh Denoising (1)
3D Object Super-Resolution (1)
Animal Action Recognition (1)
Drawing Pictures (1)
Micro-expression Generation (1)
Natural Language Transduction (1)
Part-based Representation Learning (1)
Subject-driven Video Generation (2)
2D Tiny Object Detection (1)
Brain Visual Reconstruction (1)
Image Instance Retrieval (1)
Image Recognition (3)
Image-based Automatic Meter Reading (1)
Observation Completion (1)
Pulmorary Vessel Segmentation (1)
Shape Representation Of 3D Point Clouds (1)
Sketch (4)
2D Classification (27)
3D (38)
4K 60Fps (1)
Animation (2)
Cancer (10)
Computer Vision Techniques Adopted in 3D Cryogenic Electron Microscopy (2)
Crowds (3)
Dehazing (2)
Facial Recognition and Modelling (26)
Forgery (1)
Hand (6)
Hyperspectral (4)
Image Fusion (2)
Intelligent Surveillance (1)
Remote Sensing (8)
Spectral Estimation (1)
Text-To-Image (3)
Video (34)
Visual Recognition (1)

Image Classification

166 benchmarks · 4,702 papers with code

Few-Shot Image Classification

89 benchmarks · 220 papers with code

Semi-Supervised Image Classification

58 benchmarks · 130 papers with code

Fine-Grained Image Classification

36 benchmarks · 200 papers with code

Learning with noisy labels

20 benchmarks · 143 papers with code

Small Data Image Classification

12 benchmarks · 58 papers with code

5 shown of 33 sub-tasks. All sub-tasks of Image Classification →

Semantic Segmentation

150 benchmarks · 6,644 papers with code

Semi-Supervised Semantic Segmentation

45 benchmarks · 109 papers with code

Panoptic Segmentation

27 benchmarks · 257 papers with code

3D Semantic Segmentation

19 benchmarks · 214 papers with code

Unsupervised Semantic Segmentation

18 benchmarks · 65 papers with code

Weakly-Supervised Semantic Segmentation

9 benchmarks · 169 papers with code

5 shown of 29 sub-tasks. All sub-tasks of Semantic Segmentation →

Object Detection

123 benchmarks · 4,657 papers with code

3D Object Detection

67 benchmarks · 764 papers with code

Weakly Supervised Object Detection

17 benchmarks · 58 papers with code

RGB Salient Object Detection

13 benchmarks · 99 papers with code

Few-Shot Object Detection

10 benchmarks · 97 papers with code

Real-Time Object Detection

8 benchmarks · 134 papers with code

5 shown of 39 sub-tasks. All sub-tasks of Object Detection →

Image Generation

93 benchmarks · 3,102 papers with code

Image-to-Image Translation

38 benchmarks · 550 papers with code

Text-to-Image Generation

17 benchmarks · 546 papers with code

Image Inpainting

12 benchmarks · 331 papers with code

Conditional Image Generation

11 benchmarks · 167 papers with code

Layout-to-Image Generation

11 benchmarks · 24 papers with code

5 shown of 23 sub-tasks (1 filed under another area). All sub-tasks of Image Generation →

Few-Shot Image Classification

89 benchmarks · 220 papers with code

Unsupervised Few-Shot Image Classification

4 benchmarks · 15 papers with code

Unsupervised Few-Shot Learning

0 benchmarks · 13 papers with code

Generalized Few-Shot Classification

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks (1 filed under another area).

Anomaly Detection

76 benchmarks · 1,727 papers with code

Image Manipulation Detection

21 benchmarks · 38 papers with code

Unsupervised Anomaly Detection

18 benchmarks · 226 papers with code

Anomaly Detection In Surveillance Videos

7 benchmarks · 44 papers with code

Anomaly Classification

5 benchmarks · 33 papers with code

3D Anomaly Detection

3 benchmarks · 18 papers with code

5 shown of 28 sub-tasks. All sub-tasks of Anomaly Detection →

Visual Question Answering (VQA)

76 benchmarks · 1,039 papers with code

Visual Question Answering

29 benchmarks · 1,042 papers with code

Machine Reading Comprehension

4 benchmarks · 206 papers with code

Chart Question Answering

3 benchmarks · 25 papers with code

3D Question Answering (3D-QA)

3 benchmarks · 17 papers with code

Generative Visual Question Answering

1 benchmark · 7 papers with code

5 shown of 9 sub-tasks (2 filed under another area). All sub-tasks of Visual Question Answering (VQA) →

Continuous Control

73 benchmarks · 494 papers with code

Steering Control

3 benchmarks · 7 papers with code

Car Racing

0 benchmarks · 22 papers with code

Drone Controller

0 benchmarks · 3 papers with code

3 shown of 3 sub-tasks.

Image Super-Resolution

69 benchmarks · 783 papers with code

Stereo Image Super-Resolution

10 benchmarks · 13 papers with code

Multispectral Image Super-resolution

3 benchmarks · 3 papers with code

Burst Image Super-Resolution

2 benchmarks · 10 papers with code

Multi-Frame Super-Resolution

1 benchmark · 16 papers with code

satellite image super-resolution

0 benchmarks · 4 papers with code

5 shown of 5 sub-tasks.

3D Object Detection

67 benchmarks · 764 papers with code

Monocular 3D Object Detection

16 benchmarks · 87 papers with code

Multiview Detection

5 benchmarks · 14 papers with code

3D Object Detection From Stereo Images

3 benchmarks · 12 papers with code

Robust 3D Object Detection

2 benchmarks · 16 papers with code

Robust BEV Detection

0 benchmarks · 0 papers with code

5 shown of 5 sub-tasks.

Classification

58 benchmarks · 3,778 papers with code

Graph Classification

73 benchmarks · 483 papers with code

Text Classification

68 benchmarks · 1,308 papers with code

Audio Classification

22 benchmarks · 183 papers with code

Medical Image Classification

11 benchmarks · 183 papers with code

Multi-class Classification

5 benchmarks · 289 papers with code

5 shown of 24 sub-tasks (5 filed under another area). All sub-tasks of Classification →

Domain Adaptation

58 benchmarks · 2,400 papers with code

Unsupervised Domain Adaptation

49 benchmarks · 864 papers with code

Domain Generalization

21 benchmarks · 859 papers with code

Source-Free Domain Adaptation

7 benchmarks · 103 papers with code

Partial Domain Adaptation

5 benchmarks · 20 papers with code

Universal Domain Adaptation

4 benchmarks · 31 papers with code

5 shown of 13 sub-tasks. All sub-tasks of Domain Adaptation →

Semi-Supervised Image Classification

58 benchmarks · 130 papers with code

Semi-Supervised Image Classification (Cold Start)

8 benchmarks · 1 paper with code

Open-World Semi-Supervised Learning

3 benchmarks · 13 papers with code

2 shown of 2 sub-tasks.

Action Recognition

56 benchmarks · 1,058 papers with code

Action Recognition In Videos

17 benchmarks · 71 papers with code

Action Triplet Recognition

7 benchmarks · 9 papers with code

Self-Supervised Action Recognition

6 benchmarks · 35 papers with code

Few Shot Action Recognition

5 benchmarks · 31 papers with code

3D Action Recognition

3 benchmarks · 38 papers with code

5 shown of 15 sub-tasks. All sub-tasks of Action Recognition →

Image Retrieval

56 benchmarks · 835 papers with code

Sketch-Based Image Retrieval

3 benchmarks · 40 papers with code

Composed Image Retrieval (CoIR)

2 benchmarks · 14 papers with code

Content-Based Image Retrieval

1 benchmark · 34 papers with code

Medical Image Retrieval

1 benchmark · 15 papers with code

Video-to-Shop

1 benchmark · 2 papers with code

5 shown of 10 sub-tasks. All sub-tasks of Image Retrieval →

Image Clustering

55 benchmarks · 118 papers with code

Multi-view Subspace Clustering

2 benchmarks · 17 papers with code

Online Clustering

1 benchmark · 28 papers with code

Face Clustering

1 benchmark · 22 papers with code

Multi-modal Subspace Clustering

0 benchmarks · 1 paper with code

4 shown of 4 sub-tasks.

Medical Image Segmentation

50 benchmarks · 1,080 papers with code

Brain Tumor Segmentation

12 benchmarks · 178 papers with code

Cell Segmentation

12 benchmarks · 91 papers with code

Lesion Segmentation

11 benchmarks · 269 papers with code

Retinal Vessel Segmentation

10 benchmarks · 59 papers with code

Semi-supervised Medical Image Segmentation

7 benchmarks · 79 papers with code

5 shown of 31 sub-tasks (1 filed under another area). All sub-tasks of Medical Image Segmentation →

Unsupervised Domain Adaptation

49 benchmarks · 864 papers with code

Online unsupervised domain adaptation

0 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Sentiment Analysis

42 benchmarks · 1,509 papers with code

Aspect-Based Sentiment Analysis (ABSA)

18 benchmarks · 185 papers with code

Multimodal Sentiment Analysis

5 benchmarks · 93 papers with code

Aspect Sentiment Triplet Extraction

4 benchmarks · 29 papers with code

Aspect Term Extraction and Sentiment Classification

1 benchmark · 8 papers with code

Arabic Sentiment Analysis

1 benchmark · 7 papers with code

5 shown of 12 sub-tasks (7 filed under another area). All sub-tasks of Sentiment Analysis →

Person Re-Identification

41 benchmarks · 585 papers with code

Unsupervised Person Re-Identification

19 benchmarks · 62 papers with code

Generalizable Person Re-identification

5 benchmarks · 25 papers with code

Cross-Modal Person Re-Identification

2 benchmarks · 7 papers with code

Self-Supervised Person Re-Identification

1 benchmark · 4 papers with code

Video-Based Person Re-Identification

0 benchmarks · 38 papers with code

5 shown of 13 sub-tasks. All sub-tasks of Person Re-Identification →

Visual Place Recognition

40 benchmarks · 141 papers with code

3D Place Recognition

3 benchmarks · 20 papers with code

geo-localization

0 benchmarks · 76 papers with code

Indoor Localization

0 benchmarks · 48 papers with code

3 shown of 3 sub-tasks.

Image-to-Image Translation

38 benchmarks · 550 papers with code

Cross-View Image-to-Image Translation

8 benchmarks · 8 papers with code

Multimodal Unsupervised Image-To-Image Translation

6 benchmarks · 14 papers with code

Synthetic-to-Real Translation

4 benchmarks · 58 papers with code

Unsupervised Image-To-Image Translation

2 benchmarks · 70 papers with code

Facial Makeup Transfer

2 benchmarks · 4 papers with code

5 shown of 11 sub-tasks. All sub-tasks of Image-to-Image Translation →

Instance Segmentation

36 benchmarks · 1,158 papers with code

Referring Expression Segmentation

22 benchmarks · 97 papers with code

3D Instance Segmentation

9 benchmarks · 73 papers with code

Unsupervised Object Segmentation

9 benchmarks · 23 papers with code

Real-time Instance Segmentation

8 benchmarks · 22 papers with code

Image-level Supervised Instance Segmentation

3 benchmarks · 9 papers with code

5 shown of 17 sub-tasks. All sub-tasks of Instance Segmentation →

Fine-Grained Image Classification

36 benchmarks · 200 papers with code

Displaced People Recognition

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Continual Learning

33 benchmarks · 1,142 papers with code

Class Incremental Learning

6 benchmarks · 296 papers with code

TiROD

1 benchmark · 1 paper with code

Continual Named Entity Recognition

0 benchmarks · 3 papers with code

Continual Panoptic Segmentation

0 benchmarks · 2 papers with code

unsupervised class-incremental learning

0 benchmarks · 2 papers with code

5 shown of 5 sub-tasks (1 filed under another area).

Zero-Shot Learning

33 benchmarks · 787 papers with code

Transductive Zero-Shot Classification

23 benchmarks · 3 papers with code

Temporal Action Localization

14 benchmarks · 493 papers with code

Generalized Zero-Shot Learning

12 benchmarks · 63 papers with code

GZSL Video Classification

6 benchmarks · 3 papers with code

Compositional Zero-Shot Learning

4 benchmarks · 31 papers with code

5 shown of 7 sub-tasks. All sub-tasks of Zero-Shot Learning →

Image Captioning

33 benchmarks · 774 papers with code

Semi Supervised Learning for Image Captioning

3 benchmarks · 2 papers with code

3D dense captioning

2 benchmarks · 13 papers with code

Hindi Image Captioning

2 benchmarks · 0 papers with code

Relational Captioning

1 benchmark · 2 papers with code

controllable image captioning

0 benchmarks · 8 papers with code

5 shown of 8 sub-tasks (1 filed under another area). All sub-tasks of Image Captioning →

Trajectory Prediction

32 benchmarks · 341 papers with code

Trajectory Forecasting

4 benchmarks · 89 papers with code

Out-of-Sight Trajectory Prediction

1 benchmark · 1 paper with code

Human motion prediction

0 benchmarks · 68 papers with code

3 shown of 3 sub-tasks.

Pose Estimation

31 benchmarks · 1,679 papers with code

3D Human Pose Estimation

26 benchmarks · 353 papers with code

Multi-Person Pose Estimation

13 benchmarks · 89 papers with code

Hand Pose Estimation

10 benchmarks · 103 papers with code

Head Pose Estimation

10 benchmarks · 55 papers with code

Keypoint Detection

9 benchmarks · 180 papers with code

5 shown of 17 sub-tasks. All sub-tasks of Pose Estimation →

Visual Question Answering

29 benchmarks · 1,042 papers with code

Spatial Reasoning

2 benchmarks · 198 papers with code

Explanatory Visual Question Answering

1 benchmark · 4 papers with code

Object Hallucination

0 benchmarks · 42 papers with code

Vietnamese Visual Question Answering

0 benchmarks · 4 papers with code

MM-Vet v2

0 benchmarks · 1 paper with code

5 shown of 5 sub-tasks.

Video Question Answering

28 benchmarks · 250 papers with code

Zero-Shot Video Question Answer

17 benchmarks · 73 papers with code

Few-shot Video Question Answering

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Few-Shot Learning

27 benchmarks · 1,297 papers with code

Few-Shot Semantic Segmentation

13 benchmarks · 102 papers with code

Few-Shot Audio Classification

10 benchmarks · 5 papers with code

Cross-Domain Few-Shot

9 benchmarks · 80 papers with code

Few-Shot Relation Classification

4 benchmarks · 10 papers with code

One-Shot Learning

1 benchmark · 107 papers with code

5 shown of 12 sub-tasks. All sub-tasks of Few-Shot Learning →

Panoptic Segmentation

27 benchmarks · 257 papers with code

Video Panoptic Segmentation

5 benchmarks · 21 papers with code

Uncertainty-Aware Panoptic Segmentation

1 benchmark · 3 papers with code

2 shown of 2 sub-tasks.

3D Human Pose Estimation

26 benchmarks · 353 papers with code

3D Multi-Person Pose Estimation

5 benchmarks · 35 papers with code

Egocentric Pose Estimation

4 benchmarks · 11 papers with code

Pose Prediction

3 benchmarks · 70 papers with code

Multi-Hypotheses 3D Human Pose Estimation

3 benchmarks · 13 papers with code

3D Absolute Human Pose Estimation

3 benchmarks · 9 papers with code

5 shown of 9 sub-tasks. All sub-tasks of 3D Human Pose Estimation →

Face Recognition

25 benchmarks · 639 papers with code

Lightweight Face Recognition

7 benchmarks · 12 papers with code

Synthetic Face Recognition

5 benchmarks · 7 papers with code

Age-Invariant Face Recognition

4 benchmarks · 5 papers with code

Face Quality Assessement

3 benchmarks · 3 papers with code

Face Image Quality Assessment

2 benchmarks · 24 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Face Recognition →

Visual Object Tracking

25 benchmarks · 187 papers with code

Zero-Shot Single Object Tracking

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Facial Expression Recognition (FER)

25 benchmarks · 155 papers with code

Micro-Expression Recognition

1 benchmark · 21 papers with code

3D Facial Expression Recognition

1 benchmark · 2 papers with code

Smile Recognition

1 benchmark · 0 papers with code

Cross-corpus

0 benchmarks · 22 papers with code

Micro-Expression Spotting

0 benchmarks · 4 papers with code

5 shown of 5 sub-tasks.

Novel View Synthesis

24 benchmarks · 579 papers with code

Novel LiDAR View Synthesis

0 benchmarks · 3 papers with code

Gournd video synthesis from satellite image

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Point Cloud Registration

24 benchmarks · 229 papers with code

Image to Point Cloud Registration

1 benchmark · 11 papers with code

1 shown of 1 sub-task.

Multi-Object Tracking

22 benchmarks · 279 papers with code

3D Multi-Object Tracking

6 benchmarks · 49 papers with code

Real-Time Multi-Object Tracking

0 benchmarks · 9 papers with code

Referring Multi-Object Tracking

0 benchmarks · 6 papers with code

Grounded Multiple Object Tracking

0 benchmarks · 1 paper with code

Multi-Animal Tracking with identification

0 benchmarks · 1 paper with code

5 shown of 6 sub-tasks. All sub-tasks of Multi-Object Tracking →

Referring Expression Segmentation

22 benchmarks · 97 papers with code

Generalized Referring Expression Segmentation

1 benchmark · 10 papers with code

Weakly Supervised Referring Expression Segmentation

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Domain Generalization

21 benchmarks · 859 papers with code

Single-Source Domain Generalization

2 benchmarks · 26 papers with code

Source-free Domain Generalization

0 benchmarks · 5 papers with code

Evolving Domain Generalization

0 benchmarks · 2 papers with code

3 shown of 3 sub-tasks.

Image Denoising

21 benchmarks · 509 papers with code

intensity image denoising

1 benchmark · 0 papers with code

lifetime image denoising

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Face Verification

21 benchmarks · 134 papers with code

Disguised Face Verification

2 benchmarks · 2 papers with code

1 shown of 1 sub-task.

2D Object Detection

21 benchmarks · 118 papers with code

Object Detection

123 benchmarks · 4,657 papers with code

Edge Detection

8 benchmarks · 147 papers with code

Thermal Image Segmentation

7 benchmarks · 70 papers with code

Semi-Supervised Object Detection

7 benchmarks · 51 papers with code

2D Cyclist Detection

3 benchmarks · 5 papers with code

5 shown of 15 sub-tasks. All sub-tasks of 2D Object Detection →

Video Frame Interpolation

21 benchmarks · 114 papers with code

3D Video Frame Interpolation

0 benchmarks · 1 paper with code

eXtreme-Video-Frame-Interpolation

0 benchmarks · 1 paper with code

Unsupervised Video Frame Interpolation

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks (1 filed under another area).

Video Retrieval

19 benchmarks · 255 papers with code

Video-Adverb Retrieval

5 benchmarks · 4 papers with code

Video Grounding

2 benchmarks · 56 papers with code

Video-Text Retrieval

1 benchmark · 59 papers with code

Composed Video Retrieval (CoVR)

1 benchmark · 3 papers with code

Replay Grounding

1 benchmark · 3 papers with code

5 shown of 5 sub-tasks.

3D Semantic Segmentation

19 benchmarks · 214 papers with code

Robust 3D Semantic Segmentation

3 benchmarks · 17 papers with code

Real-Time 3D Semantic Segmentation

1 benchmark · 3 papers with code

Unsupervised 3D Semantic Segmentation

1 benchmark · 3 papers with code

furniture segmentation

0 benchmarks · 1 paper with code

3D Point Cloud Part Segmentation

0 benchmarks · 0 papers with code

5 shown of 5 sub-tasks.

Video Prediction

19 benchmarks · 208 papers with code

Earth Surface Forecasting

4 benchmarks · 6 papers with code

Predict Future Video Frames

0 benchmarks · 4 papers with code

2 shown of 2 sub-tasks.

Object Localization

18 benchmarks · 282 papers with code

Weakly-Supervised Object Localization

8 benchmarks · 82 papers with code

Image-Based Localization

4 benchmarks · 25 papers with code

Unsupervised Object Localization

3 benchmarks · 7 papers with code

Monocular 3D Object Localization

0 benchmarks · 4 papers with code

Active Object Localization

0 benchmarks · 3 papers with code

5 shown of 5 sub-tasks.

Unsupervised Anomaly Detection

18 benchmarks · 226 papers with code

Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly

5 benchmarks · 4 papers with code

Root Cause Ranking

0 benchmarks · 1 paper with code

Anomaly Detection at 30% anomaly

0 benchmarks · 0 papers with code

Anomaly Detection at Various Anomaly Percentages

0 benchmarks · 0 papers with code

Unsupervised Contextual Anomaly Detection

0 benchmarks · 0 papers with code

5 shown of 5 sub-tasks.

Unsupervised Semantic Segmentation

18 benchmarks · 65 papers with code

Unsupervised Semantic Segmentation with Language-image Pre-training

12 benchmarks · 14 papers with code

1 shown of 1 sub-task.

Text-to-Image Generation

17 benchmarks · 546 papers with code

Conditional Text-to-Image Synthesis

3 benchmarks · 8 papers with code

Text-based Image Editing

1 benchmark · 29 papers with code

text-guided-image-editing

0 benchmarks · 34 papers with code

Concept Alignment

0 benchmarks · 19 papers with code

Zero-Shot Text-to-Image Generation

0 benchmarks · 11 papers with code

5 shown of 7 sub-tasks. All sub-tasks of Text-to-Image Generation →

Deblurring

17 benchmarks · 424 papers with code

Blind Image Deblurring

0 benchmarks · 19 papers with code

Single-Image Blind Deblurring

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Change Detection

17 benchmarks · 369 papers with code

Semi-supervised Change Detection

8 benchmarks · 7 papers with code

1 shown of 1 sub-task.

Action Recognition In Videos

17 benchmarks · 71 papers with code

Action Anticipation

8 benchmarks · 49 papers with code

1 shown of 1 sub-task.

Video Generation

16 benchmarks · 609 papers with code

Unconditional Video Generation

1 benchmark · 10 papers with code

Image to Video Generation

0 benchmarks · 38 papers with code

2 shown of 2 sub-tasks.

Prompt Engineering

16 benchmarks · 454 papers with code

Visual Prompting

0 benchmarks · 60 papers with code

1 shown of 1 sub-task.

Video Super-Resolution

16 benchmarks · 153 papers with code

Key-Frame-based Video Super-Resolution (K = 15)

2 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Semi-Supervised Video Object Segmentation

16 benchmarks · 99 papers with code

One-shot visual object segmentation

2 benchmarks · 26 papers with code

1 shown of 1 sub-task.

Age Estimation

16 benchmarks · 85 papers with code

Few-shot Age Estimation

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Scene Text Recognition

15 benchmarks · 146 papers with code

Jersey Number Recognition

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

Depth Estimation

14 benchmarks · 1,029 papers with code

Monocular Depth Estimation

24 benchmarks · 430 papers with code

Stereo Depth Estimation

5 benchmarks · 55 papers with code

3D Depth Estimation

1 benchmark · 12 papers with code

Stereo-LiDAR Fusion

1 benchmark · 8 papers with code

Indoor Monocular Depth Estimation

1 benchmark · 6 papers with code

5 shown of 10 sub-tasks. All sub-tasks of Depth Estimation →

Temporal Action Localization

14 benchmarks · 493 papers with code

Weakly Supervised Action Localization

9 benchmarks · 35 papers with code

Weakly-supervised Temporal Action Localization

3 benchmarks · 41 papers with code

3D Action Recognition

3 benchmarks · 38 papers with code

Temporal Action Proposal Generation

3 benchmarks · 16 papers with code

Activity Recognition In Videos

1 benchmark · 10 papers with code

5 shown of 8 sub-tasks. All sub-tasks of Temporal Action Localization →

Video Anomaly Detection

14 benchmarks · 111 papers with code

Weakly-supervised Video Anomaly Detection

2 benchmarks · 21 papers with code

1 shown of 1 sub-task.

Open Vocabulary Semantic Segmentation

14 benchmarks · 71 papers with code

Zero-Guidance Segmentation

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Image Segmentation

13 benchmarks · 2,073 papers with code

Few-shot Instance Segmentation

1 benchmark · 8 papers with code

1 shown of 1 sub-task.

Video Object Segmentation

13 benchmarks · 294 papers with code

Semi-Supervised Video Object Segmentation

16 benchmarks · 99 papers with code

Video Salient Object Detection

10 benchmarks · 20 papers with code

Unsupervised Video Object Segmentation

6 benchmarks · 52 papers with code

Referring Video Object Segmentation

5 benchmarks · 50 papers with code

Long-tail Video Object Segmentation

2 benchmarks · 2 papers with code

5 shown of 7 sub-tasks. All sub-tasks of Video Object Segmentation →

13 benchmarks · 244 papers with code

Cross-modal retrieval with noisy correspondence

3 benchmarks · 14 papers with code

Image-text matching

1 benchmark · 102 papers with code

Zero-shot Composed Person Retrieval

1 benchmark · 1 paper with code

multilingual cross-modal retrieval

0 benchmarks · 2 papers with code

Cross-Modal Retrieval on RSITMD

0 benchmarks · 0 papers with code

5 shown of 5 sub-tasks.

Video Captioning

13 benchmarks · 211 papers with code

Dense Video Captioning

4 benchmarks · 39 papers with code

Boundary Captioning

1 benchmark · 4 papers with code

Live Video Captioning

1 benchmark · 2 papers with code

Visual Text Correction

0 benchmarks · 1 paper with code

Audio-Visual Video Captioning

0 benchmarks · 0 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Video Captioning →

Gesture Recognition

13 benchmarks · 149 papers with code

Hand Gesture Recognition

18 benchmarks · 53 papers with code

Hand-Gesture Recognition

2 benchmarks · 41 papers with code

RF-based Gesture Recognition

0 benchmarks · 0 papers with code

3 shown of 3 sub-tasks.

Face Detection

13 benchmarks · 147 papers with code

Occluded Face Detection

4 benchmarks · 5 papers with code

1 shown of 1 sub-task.

Motion Synthesis

13 benchmarks · 126 papers with code

motion in-betweening

0 benchmarks · 7 papers with code

Motion Style Transfer

0 benchmarks · 6 papers with code

Temporal Human Motion Composition

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

Lane Detection

13 benchmarks · 103 papers with code

3D Lane Detection

4 benchmarks · 24 papers with code

1 shown of 1 sub-task.

Few-Shot Semantic Segmentation

13 benchmarks · 102 papers with code

Generalized Few-Shot Semantic Segmentation

4 benchmarks · 9 papers with code

1 shown of 1 sub-task.

RGB Salient Object Detection

13 benchmarks · 99 papers with code

Video Salient Object Detection

10 benchmarks · 20 papers with code

Dichotomous Image Segmentation

6 benchmarks · 26 papers with code

Co-Salient Object Detection

4 benchmarks · 22 papers with code

3 shown of 3 sub-tasks.

Multi-Person Pose Estimation

13 benchmarks · 89 papers with code

Semi-Supervised Human Pose Estimation

2 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Handwritten Text Recognition

13 benchmarks · 56 papers with code

Handwritten Document Recognition

0 benchmarks · 3 papers with code

Unsupervised Text Recognition

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Visual Reasoning

12 benchmarks · 356 papers with code

Visual Commonsense Reasoning

7 benchmarks · 33 papers with code

1 shown of 1 sub-task.

Image Inpainting

12 benchmarks · 331 papers with code

Facial Inpainting

3 benchmarks · 23 papers with code

Cloud Removal

2 benchmarks · 29 papers with code

Fine-Grained Image Inpainting

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

Video Classification

12 benchmarks · 206 papers with code

Student Engagement Level Detection (Four Class Video Classification)

1 benchmark · 1 paper with code

Multi Class Classification (Four-level Video Classification)

0 benchmarks · 0 papers with code

2 shown of 2 sub-tasks.

Cell Segmentation

12 benchmarks · 91 papers with code

Nuclei Segmentation and Classfication

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Retrieval

11 benchmarks · 5,274 papers with code

Text Retrieval

16 benchmarks · 335 papers with code

Table Retrieval

1 benchmark · 15 papers with code

Deep Hashing

0 benchmarks · 56 papers with code

3 shown of 3 sub-tasks.

Image Compression

11 benchmarks · 320 papers with code

Feature Compression

0 benchmarks · 28 papers with code

Jpeg Compression Artifact Reduction

0 benchmarks · 4 papers with code

Lossy-Compression Artifact Reduction

0 benchmarks · 3 papers with code

Color Image Compression Artifact Reduction

0 benchmarks · 0 papers with code

4 shown of 4 sub-tasks.

Action Detection

11 benchmarks · 277 papers with code

Skeleton Based Action Recognition

34 benchmarks · 219 papers with code

Human Activity Recognition

8 benchmarks · 195 papers with code

Online Action Detection

3 benchmarks · 21 papers with code

Audio-Visual Active Speaker Detection

2 benchmarks · 13 papers with code

Few Shot Temporal Action Localization

2 benchmarks · 2 papers with code

5 shown of 8 sub-tasks (1 filed under another area). All sub-tasks of Action Detection →

Conditional Image Generation

11 benchmarks · 167 papers with code

Noisy Semantic Image Synthesis

3 benchmarks · 1 paper with code

Human-Object Interaction Generation

0 benchmarks · 4 papers with code

Image-Guided Composition

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

Multiple Object Tracking

11 benchmarks · 149 papers with code

Multiple Object Tracking with Transformer

1 benchmark · 7 papers with code

Multiple Object Track and Segmentation

1 benchmark · 1 paper with code

2 shown of 2 sub-tasks.

2D Semantic Segmentation

11 benchmarks · 49 papers with code

Image Segmentation

13 benchmarks · 2,073 papers with code

Human Part Segmentation

6 benchmarks · 15 papers with code

Reflection Removal

5 benchmarks · 38 papers with code

Continual Semantic Segmentation

3 benchmarks · 17 papers with code

Text Style Transfer

2 benchmarks · 93 papers with code

5 shown of 17 sub-tasks (1 filed under another area). All sub-tasks of 2D Semantic Segmentation →

Self-Supervised Learning

10 benchmarks · 2,293 papers with code

Point Cloud Pre-training

0 benchmarks · 15 papers with code

Unsupervised Video Clustering

0 benchmarks · 0 papers with code

2 shown of 2 sub-tasks.

Quantization

10 benchmarks · 1,596 papers with code

Data Free Quantization

2 benchmarks · 16 papers with code

UNET Quantization

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Optical Flow Estimation

10 benchmarks · 795 papers with code

Video Stabilization

0 benchmarks · 28 papers with code

1 shown of 1 sub-task.

3D Reconstruction

10 benchmarks · 793 papers with code

3D Semantic Scene Completion

4 benchmarks · 34 papers with code

3D Room Layouts From A Single RGB Panorama

3 benchmarks · 9 papers with code

Unsupervised 3D Human Pose Estimation

2 benchmarks · 7 papers with code

Garment Reconstruction

1 benchmark · 15 papers with code

Point cloud reconstruction

0 benchmarks · 46 papers with code

5 shown of 7 sub-tasks. All sub-tasks of 3D Reconstruction →

Object Tracking

10 benchmarks · 767 papers with code

Visual Object Tracking

25 benchmarks · 187 papers with code

Multi-Object Tracking

22 benchmarks · 279 papers with code

Multiple Object Tracking

11 benchmarks · 149 papers with code

Online Multi-Object Tracking

6 benchmarks · 30 papers with code

Sports Ball Detection and Tracking

5 benchmarks · 5 papers with code

5 shown of 10 sub-tasks. All sub-tasks of Object Tracking →

Multi-Label Classification

10 benchmarks · 459 papers with code

Hierarchical Multi-label Classification

20 benchmarks · 19 papers with code

Medical Code Prediction

7 benchmarks · 16 papers with code

Missing Labels

0 benchmarks · 50 papers with code

Extreme Multi-Label Classification

0 benchmarks · 31 papers with code

4 shown of 4 sub-tasks (2 filed under another area).

Visual Tracking

10 benchmarks · 202 papers with code

Point Tracking

8 benchmarks · 61 papers with code

Rgb-T Tracking

4 benchmarks · 25 papers with code

Real-Time Visual Tracking

0 benchmarks · 10 papers with code

RF-based Visual Tracking

0 benchmarks · 0 papers with code

4 shown of 4 sub-tasks.

Keyword Spotting

10 benchmarks · 113 papers with code

Visual Keyword Spotting

3 benchmarks · 4 papers with code

Small-Footprint Keyword Spotting

0 benchmarks · 9 papers with code

2 shown of 2 sub-tasks.

Hand Pose Estimation

10 benchmarks · 103 papers with code

3D Hand Pose Estimation

7 benchmarks · 87 papers with code

1 shown of 1 sub-task.

Few-Shot Object Detection

10 benchmarks · 97 papers with code

Cross-Domain Few-Shot Object Detection

6 benchmarks · 14 papers with code

1 shown of 1 sub-task.

Object Counting

10 benchmarks · 81 papers with code

Few-shot Object Counting and Detection

2 benchmarks · 4 papers with code

Training-free Object Counting

2 benchmarks · 1 paper with code

Exemplar-Free Counting

1 benchmark · 8 papers with code

Open-vocabulary object counting

0 benchmarks · 1 paper with code

4 shown of 4 sub-tasks.

2D Human Pose Estimation

10 benchmarks · 68 papers with code

Action Anticipation

8 benchmarks · 49 papers with code

Style Transfer

3 benchmarks · 759 papers with code

3D Face Animation

3 benchmarks · 25 papers with code

Community Question Answering

2 benchmarks · 50 papers with code

Semi-Supervised Human Pose Estimation

2 benchmarks · 3 papers with code

5 shown of 6 sub-tasks. All sub-tasks of 2D Human Pose Estimation →

Retinal Vessel Segmentation

10 benchmarks · 59 papers with code

Artery/Veins Retinal Vessel Segmentation

5 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Facial Landmark Detection

10 benchmarks · 52 papers with code

Unsupervised Facial Landmark Detection

6 benchmarks · 13 papers with code

3D Facial Landmark Localization

4 benchmarks · 4 papers with code

Speech to Facial Landmark

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

Fairness

9 benchmarks · 1,714 papers with code

Exposure Fairness

0 benchmarks · 8 papers with code

1 shown of 1 sub-task.

Emotion Recognition

9 benchmarks · 614 papers with code

Speech Emotion Recognition

16 benchmarks · 139 papers with code

Emotion Recognition in Conversation

16 benchmarks · 83 papers with code

Multimodal Emotion Recognition

7 benchmarks · 80 papers with code

Emotion Recognition in Context

4 benchmarks · 5 papers with code

EEG Emotion Recognition

3 benchmarks · 14 papers with code

5 shown of 12 sub-tasks (1 filed under another area). All sub-tasks of Emotion Recognition →

Object Recognition

9 benchmarks · 577 papers with code

3D Object Recognition

4 benchmarks · 32 papers with code

Depiction Invariant Object Recognition

1 benchmark · 1 paper with code

Continuous Object Recognition

0 benchmarks · 2 papers with code

3 shown of 3 sub-tasks.

Image Deblurring

9 benchmarks · 167 papers with code

Low-light Image Deblurring and Enhancement

1 benchmark · 3 papers with code

1 shown of 1 sub-task.

Pedestrian Detection

9 benchmarks · 132 papers with code

Thermal Infrared Pedestrian Detection

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Action Segmentation

9 benchmarks · 99 papers with code

Unsupervised Action Segmentation

4 benchmarks · 9 papers with code

Weakly Supervised Action Segmentation (Transcript)

1 benchmark · 4 papers with code

Weakly Supervised Action Segmentation (Action Set))

1 benchmark · 1 paper with code

Skeleton Based Action Segmentation

0 benchmarks · 6 papers with code

4 shown of 4 sub-tasks.

Scene Text Detection

9 benchmarks · 98 papers with code

Curved Text Detection

1 benchmark · 9 papers with code

Multi-Oriented Scene Text Detection

1 benchmark · 2 papers with code

2 shown of 2 sub-tasks.

3D Face Reconstruction

9 benchmarks · 83 papers with code

Facial Recognition and Modelling

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Cross-Domain Few-Shot

9 benchmarks · 80 papers with code

cross-domain few-shot learning

1 benchmark · 37 papers with code

1 shown of 1 sub-task.

3D Instance Segmentation

9 benchmarks · 73 papers with code

Interactive 3D Instance Segmentation

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Single-View 3D Reconstruction

9 benchmarks · 51 papers with code

3D Semantic Scene Completion from a single RGB image

3 benchmarks · 11 papers with code

1 shown of 1 sub-task.

2D Pose Estimation

9 benchmarks · 46 papers with code

Category-Agnostic Pose Estimation

1 benchmark · 11 papers with code

Overlapping Pose Estimation

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Image Reconstruction

8 benchmarks · 712 papers with code

Blind Super-Resolution

18 benchmarks · 44 papers with code

MRI Reconstruction

6 benchmarks · 198 papers with code

CT Reconstruction

0 benchmarks · 67 papers with code

Film Removal

0 benchmarks · 1 paper with code

WiFi CSI-based Image Reconstruction

0 benchmarks · 1 paper with code

5 shown of 5 sub-tasks (1 filed under another area).

DeepFake Detection

8 benchmarks · 237 papers with code

Audio Deepfake Detection

2 benchmarks · 35 papers with code

Multimodal Forgery Detection

1 benchmark · 1 paper with code

Synthetic Speech Detection

0 benchmarks · 12 papers with code

diffusion-generated faces detection

0 benchmarks · 1 paper with code

Human Detection of Deepfakes

0 benchmarks · 1 paper with code

5 shown of 5 sub-tasks.

Boundary Detection

8 benchmarks · 123 papers with code

Junction Detection

0 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Image Matting

8 benchmarks · 110 papers with code

Semantic Image Matting

1 benchmark · 4 papers with code

1 shown of 1 sub-task.

No-Reference Image Quality Assessment

8 benchmarks · 103 papers with code

NR-IQA

1 benchmark · 8 papers with code

Blind Image Quality Assessment

0 benchmarks · 6 papers with code

2 shown of 2 sub-tasks.

Lipreading

8 benchmarks · 36 papers with code

Landmark-based Lipreading

2 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Human Interaction Recognition

8 benchmarks · 8 papers with code

One-Shot 3D Action Recognition

1 benchmark · 7 papers with code

Dense contact estimation

1 benchmark · 4 papers with code

Mutual Gaze

0 benchmarks · 3 papers with code

3 shown of 3 sub-tasks.

Image/Document Clustering

8 benchmarks · 6 papers with code

Self-Organized Clustering

0 benchmarks · 4 papers with code

1 shown of 1 sub-task.

Knowledge Distillation

7 benchmarks · 1,740 papers with code

Data-free Knowledge Distillation

2 benchmarks · 37 papers with code

Self-Knowledge Distillation

0 benchmarks · 36 papers with code

2 shown of 2 sub-tasks (1 filed under another area).

Image Enhancement

7 benchmarks · 445 papers with code

UIE

28 benchmarks · 39 papers with code

Low-Light Image Enhancement

22 benchmarks · 181 papers with code

Image Relighting

2 benchmarks · 32 papers with code

Local Color Enhancement

1 benchmark · 3 papers with code

De-aliasing

0 benchmarks · 9 papers with code

5 shown of 10 sub-tasks. All sub-tasks of Image Enhancement →

Facial Expression Recognition

7 benchmarks · 164 papers with code

Cross-Domain Facial Expression Recognition

2 benchmarks · 4 papers with code

Zero-Shot Facial Expression Recognition

1 benchmark · 2 papers with code

2 shown of 2 sub-tasks.

Scene Graph Generation

7 benchmarks · 151 papers with code

Unbiased Scene Graph Generation

1 benchmark · 16 papers with code

Panoptic Scene Graph Generation

1 benchmark · 14 papers with code

2 shown of 2 sub-tasks.

Saliency Detection

7 benchmarks · 137 papers with code

Video Saliency Detection

5 benchmarks · 21 papers with code

Saliency Prediction

4 benchmarks · 105 papers with code

Co-Salient Object Detection

4 benchmarks · 22 papers with code

Unsupervised Saliency Detection

3 benchmarks · 5 papers with code

4 shown of 4 sub-tasks.

Source-Free Domain Adaptation

7 benchmarks · 103 papers with code

3D Source-Free Domain Adaptation

6 benchmarks · 1 paper with code

Source Free Object Detection

2 benchmarks · 12 papers with code

2 shown of 2 sub-tasks.

3D Hand Pose Estimation

7 benchmarks · 87 papers with code

3D Canonical Hand Pose Estimation

3 benchmarks · 0 papers with code

hand-object pose

2 benchmarks · 18 papers with code

Grasp Generation

0 benchmarks · 21 papers with code

3 shown of 3 sub-tasks.

Multimodal Emotion Recognition

7 benchmarks · 80 papers with code

Video Emotion Detection

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Multi-Label Image Classification

7 benchmarks · 58 papers with code

Multi-label Image Recognition with Partial Labels

3 benchmarks · 8 papers with code

1 shown of 1 sub-task.

Talking Head Generation

7 benchmarks · 51 papers with code

Unconstrained Lip-synchronization

3 benchmarks · 4 papers with code

1 shown of 1 sub-task.

Camouflaged Object Segmentation

7 benchmarks · 38 papers with code

Camouflaged Object Segmentation with a Single Task-generic Prompt

3 benchmarks · 2 papers with code

1 shown of 1 sub-task.

Human action generation

7 benchmarks · 10 papers with code

Action Generation

0 benchmarks · 49 papers with code

1 shown of 1 sub-task.

Denoising

6 benchmarks · 2,838 papers with code

Color Image Denoising

80 benchmarks · 32 papers with code

Grayscale Image Denoising

41 benchmarks · 9 papers with code

Image Denoising

21 benchmarks · 509 papers with code

Salt-And-Pepper Noise Removal

6 benchmarks · 5 papers with code

Sar Image Despeckling

0 benchmarks · 11 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Denoising →

regression

6 benchmarks · 2,445 papers with code

Travel Time Estimation

1 benchmark · 19 papers with code

quantile regression

0 benchmarks · 102 papers with code

2 shown of 2 sub-tasks.

Optical Character Recognition (OCR)

6 benchmarks · 462 papers with code

Handwritten Text Recognition

13 benchmarks · 56 papers with code

Handwriting Recognition

3 benchmarks · 53 papers with code

Handwritten Digit Recognition

2 benchmarks · 29 papers with code

Active Learning

1 benchmark · 913 papers with code

Irregular Text Recognition

0 benchmarks · 5 papers with code

5 shown of 10 sub-tasks. All sub-tasks of Optical Character Recognition (OCR) →

Class Incremental Learning

6 benchmarks · 296 papers with code

Few-Shot Class-Incremental Learning

3 benchmarks · 55 papers with code

Non-exemplar-based Class Incremental Learning

3 benchmarks · 2 papers with code

Class-Incremental Semantic Segmentation

0 benchmarks · 16 papers with code

3 shown of 3 sub-tasks.

Salient Object Detection

6 benchmarks · 276 papers with code

Saliency Ranking

0 benchmarks · 9 papers with code

RGB-T Salient Object Detection

0 benchmarks · 6 papers with code

2 shown of 2 sub-tasks.

Human-Object Interaction Detection

6 benchmarks · 173 papers with code

Affordance Recognition

2 benchmarks · 7 papers with code

Hand-Object Interaction Detection

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Scene Segmentation

6 benchmarks · 141 papers with code

Thermal Image Segmentation

7 benchmarks · 70 papers with code

1 shown of 1 sub-task.

6 benchmarks · 132 papers with code

ObjectGoal Navigation

0 benchmarks · 4 papers with code

1 shown of 1 sub-task (1 filed under another area).

6D Pose Estimation

6 benchmarks · 118 papers with code

hand-object pose

2 benchmarks · 18 papers with code

Robot Pose Estimation

1 benchmark · 3 papers with code

2 shown of 2 sub-tasks.

Text-to-Video Generation

6 benchmarks · 97 papers with code

Text-to-Video Editing

0 benchmarks · 6 papers with code

Subject-driven Video Generation

0 benchmarks · 2 papers with code

2 shown of 2 sub-tasks.

Video Summarization

6 benchmarks · 89 papers with code

Unsupervised Video Summarization

2 benchmarks · 19 papers with code

Supervised Video Summarization

2 benchmarks · 12 papers with code

2 shown of 2 sub-tasks.

Semantic correspondence

6 benchmarks · 88 papers with code

Interspecies Facial Keypoint Transfer

2 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Document Layout Analysis

6 benchmarks · 47 papers with code

MS-SSIM

1 benchmark · 61 papers with code

1 shown of 1 sub-task.

Key Information Extraction

6 benchmarks · 40 papers with code

Key-value Pair Extraction

2 benchmarks · 9 papers with code

1 shown of 1 sub-task.

Unsupervised Panoptic Segmentation

6 benchmarks · 4 papers with code

Unsupervised Zero-Shot Panoptic Segmentation

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Segmentation

5 benchmarks · 5,255 papers with code

Open-Vocabulary Semantic Segmentation

0 benchmarks · 54 papers with code

1 shown of 1 sub-task.

Representation Learning

5 benchmarks · 4,662 papers with code

Disentanglement

3 benchmarks · 744 papers with code

Graph Representation Learning

1 benchmark · 479 papers with code

Feature Upsampling

1 benchmark · 22 papers with code

Sentence Embeddings

0 benchmarks · 255 papers with code

Network Embedding

0 benchmarks · 165 papers with code

5 shown of 14 sub-tasks (2 filed under another area). All sub-tasks of Representation Learning →

Video Semantic Segmentation

5 benchmarks · 418 papers with code

Camera shot segmentation

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Image Registration

5 benchmarks · 332 papers with code

distortion correction

0 benchmarks · 18 papers with code

Unsupervised Image Registration

0 benchmarks · 12 papers with code

2 shown of 2 sub-tasks.

Multi-class Classification

5 benchmarks · 289 papers with code

Patent classification

0 benchmarks · 9 papers with code

1 shown of 1 sub-task.

3D Point Cloud Classification

5 benchmarks · 150 papers with code

Few-Shot 3D Point Cloud Classification

8 benchmarks · 29 papers with code

3D Object Classification

4 benchmarks · 47 papers with code

Zero-Shot Transfer 3D Point Cloud Classification

3 benchmarks · 11 papers with code

Supervised Only 3D Point Cloud Classification

1 benchmark · 13 papers with code

4 shown of 4 sub-tasks.

Scene Flow Estimation

5 benchmarks · 81 papers with code

Self-supervised Scene Flow Estimation

1 benchmark · 15 papers with code

1 shown of 1 sub-task.

Shadow Removal

5 benchmarks · 71 papers with code

Document Shadow Removal

0 benchmarks · 15 papers with code

1 shown of 1 sub-task.

Stereo Depth Estimation

5 benchmarks · 55 papers with code

Omnnidirectional Stereo Depth Estimation

1 benchmark · 6 papers with code

1 shown of 1 sub-task.

Visual Relationship Detection

5 benchmarks · 37 papers with code

Video Visual Relation Detection

2 benchmarks · 9 papers with code

Human-Object Relationship Detection

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

3D Multi-Person Pose Estimation

5 benchmarks · 35 papers with code

3D Multi-Person Mesh Recovery

2 benchmarks · 12 papers with code

3D Multi-Person Pose Estimation (absolute)

1 benchmark · 12 papers with code

3D Multi-Person Pose Estimation (root-relative)

1 benchmark · 11 papers with code

3 shown of 3 sub-tasks.

Anomaly Classification

5 benchmarks · 33 papers with code

Anomaly Severity Classification (Anomaly vs. Defect)

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Unified Image Restoration

5 benchmarks · 11 papers with code

Blind All-in-One Image Restoration

2 benchmarks · 10 papers with code

1 shown of 1 sub-task.

Video-Adverb Retrieval

5 benchmarks · 4 papers with code

Video-Adverb Retrieval (Unseen Compositions)

3 benchmarks · 2 papers with code

1 shown of 1 sub-task.

Reconstruction

5 benchmarks · 2 papers with code

3D Human Reconstruction

10 benchmarks · 59 papers with code

Single-View 3D Reconstruction

9 benchmarks · 51 papers with code

Single-Image-Based Hdr Reconstruction

1 benchmark · 4 papers with code

4D reconstruction

0 benchmarks · 29 papers with code

4 shown of 4 sub-tasks.

Autonomous Driving

4 benchmarks · 2,091 papers with code

Motion Forecasting

1 benchmark · 88 papers with code

Bench2Drive

1 benchmark · 19 papers with code

NavSim

1 benchmark · 14 papers with code

CARLA MAP Leaderboard

1 benchmark · 6 papers with code

3D Pedestrian Tracking

1 benchmark · 4 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Autonomous Driving →

Meta-Learning

4 benchmarks · 1,408 papers with code

Few-Shot Learning

27 benchmarks · 1,297 papers with code

Sample Probing

0 benchmarks · 1 paper with code

universal meta-learning

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

Binary Classification

4 benchmarks · 710 papers with code

Cancer-no cancer per breast classification

2 benchmarks · 2 papers with code

Cancer-no cancer per image classification

1 benchmark · 2 papers with code

Stable MCI vs Progressive MCI

1 benchmark · 1 paper with code

Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification

1 benchmark · 1 paper with code

LLM-generated Text Detection

0 benchmarks · 11 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Binary Classification →

Imputation

4 benchmarks · 479 papers with code

Multivariate Time Series Imputation

9 benchmarks · 29 papers with code

1 shown of 1 sub-task.

Activity Recognition

4 benchmarks · 330 papers with code

Action Recognition

56 benchmarks · 1,058 papers with code

Multimodal Activity Recognition

10 benchmarks · 12 papers with code

Human Activity Recognition

8 benchmarks · 195 papers with code

Human action generation

7 benchmarks · 10 papers with code

Group Activity Recognition

2 benchmarks · 18 papers with code

5 shown of 11 sub-tasks (2 filed under another area). All sub-tasks of Activity Recognition →

Visual Grounding

4 benchmarks · 299 papers with code

Person-centric Visual Grounding

1 benchmark · 4 papers with code

3D visual grounding

0 benchmarks · 39 papers with code

Phrase Extraction and Grounding (PEG)

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

4 benchmarks · 164 papers with code

PointGoal Navigation

1 benchmark · 15 papers with code

Social Navigation

0 benchmarks · 22 papers with code

ObjectGoal Navigation

0 benchmarks · 4 papers with code

Sequential Place Learning

0 benchmarks · 4 papers with code

VNLA

0 benchmarks · 1 paper with code

5 shown of 5 sub-tasks (1 filed under another area).

Saliency Prediction

4 benchmarks · 105 papers with code

Few-Shot Transfer Learning for Saliency Prediction

4 benchmarks · 1 paper with code

Aerial Video Saliency Prediction

0 benchmarks · 0 papers with code

2 shown of 2 sub-tasks.

Open Vocabulary Object Detection

4 benchmarks · 92 papers with code

Open Vocabulary Attribute Detection

2 benchmarks · 12 papers with code

1 shown of 1 sub-task.

3D Object Reconstruction

4 benchmarks · 73 papers with code

CAD Reconstruction

3 benchmarks · 10 papers with code

3D Object Reconstruction From A Single Image

2 benchmarks · 10 papers with code

Simulated Gaussian Manipulation

0 benchmarks · 5 papers with code

Feature Splatting

0 benchmarks · 4 papers with code

4 shown of 4 sub-tasks.

Small Object Detection

4 benchmarks · 60 papers with code

Rice Grain Disease Detection

1 benchmark · 0 papers with code

1 shown of 1 sub-task.

Point Cloud Generation

4 benchmarks · 59 papers with code

Point Cloud Completion

3 benchmarks · 97 papers with code

1 shown of 1 sub-task.

3D Object Classification

4 benchmarks · 47 papers with code

Generative 3D Object Classification

2 benchmarks · 5 papers with code

Cube Engraving Classification

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Dense Video Captioning

4 benchmarks · 39 papers with code

Zero-shot dense video captioning

2 benchmarks · 0 papers with code

1 shown of 1 sub-task.

3D Semantic Scene Completion

4 benchmarks · 34 papers with code

3D Semantic Scene Completion from a single RGB image

3 benchmarks · 11 papers with code

1 shown of 1 sub-task.

Surgical phase recognition

4 benchmarks · 31 papers with code

Online surgical phase recognition

0 benchmarks · 8 papers with code

Offline surgical phase recognition

0 benchmarks · 2 papers with code

2 shown of 2 sub-tasks.

Document Text Classification

4 benchmarks · 5 papers with code

Learning with noisy labels

20 benchmarks · 143 papers with code

Multi-Label Classification Of Biomedical Texts

2 benchmarks · 4 papers with code

Political Salient Issue Orientation Detection

1 benchmark · 3 papers with code

3 shown of 3 sub-tasks (1 filed under another area).

Meter Reading

4 benchmarks · 3 papers with code

Image-based Automatic Meter Reading

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Few-Shot Transfer Learning for Saliency Prediction

4 benchmarks · 1 paper with code

Saliency Prediction

4 benchmarks · 105 papers with code

1 shown of 1 sub-task.

Data Augmentation

3 benchmarks · 3,225 papers with code

Image Augmentation

1 benchmark · 127 papers with code

Text Augmentation

0 benchmarks · 41 papers with code

2 shown of 2 sub-tasks.

Style Transfer

3 benchmarks · 759 papers with code

Image Stylization

0 benchmarks · 30 papers with code

Font Style Transfer

0 benchmarks · 5 papers with code

Style Generalization

0 benchmarks · 5 papers with code

Face Transfer

0 benchmarks · 4 papers with code

Reverse Style Transfer

0 benchmarks · 3 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Style Transfer →

Adversarial Attack

3 benchmarks · 745 papers with code

Backdoor Attack

0 benchmarks · 217 papers with code

Adversarial Text

0 benchmarks · 51 papers with code

Adversarial Attack Detection

0 benchmarks · 16 papers with code

Real-World Adversarial Attack

0 benchmarks · 13 papers with code

4 shown of 4 sub-tasks (2 filed under another area).

Scene Understanding

3 benchmarks · 720 papers with code

Video Semantic Segmentation

5 benchmarks · 418 papers with code

Visual Relationship Detection

5 benchmarks · 37 papers with code

3D Room Layouts From A Single RGB Panorama

3 benchmarks · 9 papers with code

Outdoor Light Source Estimation

1 benchmark · 1 paper with code

Lighting Estimation

0 benchmarks · 18 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Scene Understanding →

Image Quality Assessment

3 benchmarks · 318 papers with code

No-Reference Image Quality Assessment

8 benchmarks · 103 papers with code

Full reference image quality assessment

4 benchmarks · 14 papers with code

Aesthetics Quality Assessment

4 benchmarks · 12 papers with code

Full-Reference Image Quality Assessment

0 benchmarks · 13 papers with code

Stereoscopic image quality assessment

0 benchmarks · 6 papers with code

5 shown of 7 sub-tasks. All sub-tasks of Image Quality Assessment →

Multimodal Reasoning

3 benchmarks · 138 papers with code

MME

0 benchmarks · 47 papers with code

1 shown of 1 sub-task.

Point Cloud Completion

3 benchmarks · 97 papers with code

Point Cloud Semantic Completion

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Pose Tracking

3 benchmarks · 76 papers with code

3D Human Pose Tracking

1 benchmark · 4 papers with code

1 shown of 1 sub-task (1 filed under another area).

Zero-Shot Image Classification

3 benchmarks · 64 papers with code

Open Vocabulary Image Classification

4 benchmarks · 6 papers with code

1 shown of 1 sub-task.

Image Colorization

3 benchmarks · 63 papers with code

Sketch Colorization

0 benchmarks · 7 papers with code

1 shown of 1 sub-task.

Handwriting Recognition

3 benchmarks · 53 papers with code

Handwritten Word Segmentation

2 benchmarks · 2 papers with code

Handwritten Line Segmentation

1 benchmark · 2 papers with code

2 shown of 2 sub-tasks.

Text to Video Retrieval

3 benchmarks · 51 papers with code

Partially Relevant Video Retrieval

3 benchmarks · 5 papers with code

1 shown of 1 sub-task.

Weakly-supervised Temporal Action Localization

3 benchmarks · 41 papers with code

Weakly Supervised Temporal Action Localization

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Sketch-Based Image Retrieval

3 benchmarks · 40 papers with code

On-the-Fly Sketch Based Image Retrieval

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

3D Action Recognition

3 benchmarks · 38 papers with code

Skeleton Based Action Recognition

34 benchmarks · 219 papers with code

Image Manipulation Detection

21 benchmarks · 38 papers with code

Zero Shot Skeletal Action Recognition

3 benchmarks · 7 papers with code

Generalized Zero Shot skeletal action recognition

3 benchmarks · 3 papers with code

Model Editing

0 benchmarks · 107 papers with code

5 shown of 6 sub-tasks (1 filed under another area). All sub-tasks of 3D Action Recognition →

Multimodal Machine Translation

3 benchmarks · 38 papers with code

Multimodal Lexical Translation

4 benchmarks · 2 papers with code

Face to Face Translation

0 benchmarks · 4 papers with code

2 shown of 2 sub-tasks.

Road Segmentation

3 benchmarks · 34 papers with code

Lane Labeling

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Meme Classification

3 benchmarks · 30 papers with code

Hateful Meme Classification

4 benchmarks · 9 papers with code

1 shown of 1 sub-task.

3D Face Animation

3 benchmarks · 25 papers with code

Video Super-Resolution

16 benchmarks · 153 papers with code

1 shown of 1 sub-task.

10-shot image generation

3 benchmarks · 21 papers with code

Semantic Segmentation

150 benchmarks · 6,644 papers with code

Text-to-Image Generation

17 benchmarks · 546 papers with code

Deblurring

17 benchmarks · 424 papers with code

Motion Synthesis

13 benchmarks · 126 papers with code

Image Deblurring

9 benchmarks · 167 papers with code

5 shown of 21 sub-tasks (3 filed under another area). All sub-tasks of 10-shot image generation →

Stereo Disparity Estimation

3 benchmarks · 19 papers with code

Stereo Matching

0 benchmarks · 192 papers with code

1 shown of 1 sub-task.

3D Anomaly Detection

3 benchmarks · 18 papers with code

Video Anomaly Detection

14 benchmarks · 111 papers with code

Artifact Detection

1 benchmark · 17 papers with code

2 shown of 2 sub-tasks.

Continual Semantic Segmentation

3 benchmarks · 17 papers with code

Overlapped 5-3

1 benchmark · 3 papers with code

Overlapped 25-25

1 benchmark · 1 paper with code

2 shown of 2 sub-tasks.

3D Absolute Human Pose Estimation

3 benchmarks · 9 papers with code

3D Face Animation

3 benchmarks · 25 papers with code

3D Human Shape Estimation

2 benchmarks · 19 papers with code

Image to 3D

0 benchmarks · 54 papers with code

Text-to-Face Generation

0 benchmarks · 5 papers with code

4 shown of 4 sub-tasks.

2D Panoptic Segmentation

3 benchmarks · 4 papers with code

Unsupervised Panoptic Segmentation

6 benchmarks · 4 papers with code

1 shown of 1 sub-task.

Traffic Accident Detection

3 benchmarks · 4 papers with code

Accident Anticipation

1 benchmark · 5 papers with code

1 shown of 1 sub-task.

Face Quality Assessement

3 benchmarks · 3 papers with code

Face Image Quality

0 benchmarks · 23 papers with code

1 shown of 1 sub-task.

Reinforcement Learning (RL)

2 benchmarks · 4,749 papers with code

3D Point Cloud Reinforcement Learning

1 benchmark · 2 papers with code

RoomEnv-v0

1 benchmark · 1 paper with code

RoomEnv-v1

1 benchmark · 1 paper with code

RoomEnv-v2

1 benchmark · 1 paper with code

Off-policy evaluation

0 benchmarks · 102 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Reinforcement Learning (RL) →

Dimensionality Reduction

2 benchmarks · 857 papers with code

Supervised dimensionality reduction

0 benchmarks · 18 papers with code

Online nonnegative CP decomposition

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Image Restoration

2 benchmarks · 666 papers with code

JPEG Artifact Correction

39 benchmarks · 12 papers with code

Blind Super-Resolution

18 benchmarks · 44 papers with code

Unified Image Restoration

5 benchmarks · 11 papers with code

Spectral Reconstruction

4 benchmarks · 37 papers with code

Underwater Image Restoration

1 benchmark · 25 papers with code

5 shown of 13 sub-tasks. All sub-tasks of Image Restoration →

Medical Diagnosis

2 benchmarks · 222 papers with code

Retinal OCT Disease Classification

2 benchmarks · 10 papers with code

Alzheimer's Disease Detection

1 benchmark · 26 papers with code

Thoracic Disease Classification

1 benchmark · 4 papers with code

Blood Cell Count

0 benchmarks · 3 papers with code

CBC TEST

0 benchmarks · 2 papers with code

5 shown of 5 sub-tasks.

Colorization

2 benchmarks · 177 papers with code

Point-interactive Image Colorization

3 benchmarks · 4 papers with code

Line Art Colorization

0 benchmarks · 5 papers with code

Color Mismatch Correction

0 benchmarks · 2 papers with code

3 shown of 3 sub-tasks.

Rain Removal

2 benchmarks · 167 papers with code

Single Image Deraining

9 benchmarks · 59 papers with code

1 shown of 1 sub-task.

Point Cloud Classification

2 benchmarks · 138 papers with code

Few-Shot Point Cloud Classification

3 benchmarks · 3 papers with code

Jet Tagging

1 benchmark · 21 papers with code

2 shown of 2 sub-tasks.

Scene Parsing

2 benchmarks · 80 papers with code

Scene Text Recognition

15 benchmarks · 146 papers with code

Scene Recognition

8 benchmarks · 68 papers with code

Scene Graph Generation

7 benchmarks · 151 papers with code

Face Parsing

4 benchmarks · 22 papers with code

Scene Understanding

3 benchmarks · 720 papers with code

5 shown of 9 sub-tasks. All sub-tasks of Scene Parsing →

Moment Retrieval

2 benchmarks · 76 papers with code

Zero-shot Moment Retrieval

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Unsupervised Image-To-Image Translation

2 benchmarks · 70 papers with code

Sensor Modeling

0 benchmarks · 11 papers with code

1 shown of 1 sub-task.

Gait Recognition

2 benchmarks · 68 papers with code

Multiview Gait Recognition

2 benchmarks · 9 papers with code

Gait Recognition in the Wild

1 benchmark · 9 papers with code

2 shown of 2 sub-tasks.

3D Shape Reconstruction

2 benchmarks · 66 papers with code

3D Shape Reconstruction From A Single 2D Image

2 benchmarks · 8 papers with code

1 shown of 1 sub-task.

Human Parsing

2 benchmarks · 62 papers with code

Multi-Human Parsing

3 benchmarks · 10 papers with code

1 shown of 1 sub-task.

Visual Speech Recognition

2 benchmarks · 62 papers with code

Lip to Speech Synthesis

1 benchmark · 6 papers with code

1 shown of 1 sub-task.

Video Grounding

2 benchmarks · 56 papers with code

Boundary Grounding

1 benchmark · 1 paper with code

Video Narrative Grounding

0 benchmarks · 2 papers with code

2 shown of 2 sub-tasks.

Camera Localization

2 benchmarks · 52 papers with code

Cross-View Geo-Localisation

6 benchmarks · 9 papers with code

Camera Relocalization

0 benchmarks · 22 papers with code

2 shown of 2 sub-tasks.

Shadow Detection

2 benchmarks · 46 papers with code

Shadow Detection And Removal

0 benchmarks · 7 papers with code

1 shown of 1 sub-task.

Talking Face Generation

2 benchmarks · 43 papers with code

Constrained Lip-synchronization

0 benchmarks · 6 papers with code

Face Dubbing

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

3D Object Tracking

2 benchmarks · 42 papers with code

3D Single Object Tracking

0 benchmarks · 26 papers with code

1 shown of 1 sub-task.

Patch Matching

2 benchmarks · 42 papers with code

Multimodal Patch Matching

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Video Restoration

2 benchmarks · 42 papers with code

Analog Video Restoration

1 benchmark · 7 papers with code

1 shown of 1 sub-task.

Single-Source Domain Generalization

2 benchmarks · 26 papers with code

Photo to Rest Generalization

2 benchmarks · 3 papers with code

1 shown of 1 sub-task.

3D Face Modelling

2 benchmarks · 21 papers with code

Continuous Control

73 benchmarks · 494 papers with code

Facial Recognition and Modelling

0 benchmarks · 0 papers with code

2 shown of 2 sub-tasks.

Point Clouds

2 benchmarks · 19 papers with code

Cross-modal place recognition

0 benchmarks · 5 papers with code

point cloud video understanding

0 benchmarks · 4 papers with code

Point Cloud Rrepresentation Learning

0 benchmarks · 0 papers with code

3 shown of 3 sub-tasks.

Image Matching

2 benchmarks · 16 papers with code

Semantic correspondence

6 benchmarks · 88 papers with code

Patch Matching

2 benchmarks · 42 papers with code

set matching

0 benchmarks · 19 papers with code

Matching Disparate Images

0 benchmarks · 0 papers with code

4 shown of 4 sub-tasks.

Composed Image Retrieval (CoIR)

2 benchmarks · 14 papers with code

Zero-Shot Composed Image Retrieval (ZS-CIR)

12 benchmarks · 25 papers with code

1 shown of 1 sub-task.

Landmark Recognition

2 benchmarks · 14 papers with code

Brain landmark detection

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

Abnormal Event Detection In Video

2 benchmarks · 13 papers with code

Semi-supervised Anomaly Detection

1 benchmark · 37 papers with code

1 shown of 1 sub-task.

Lung Nodule Detection

2 benchmarks · 13 papers with code

Lung Nodule 3D Detection

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Breast Cancer Histology Image Classification

2 benchmarks · 12 papers with code

Breast Cancer Detection

4 benchmarks · 40 papers with code

Breast Cancer Histology Image Classification (20% labels)

1 benchmark · 1 paper with code

2 shown of 2 sub-tasks.

The Semantic Segmentation Of Remote Sensing Imagery

2 benchmarks · 11 papers with code

Lake Ice Monitoring

0 benchmarks · 6 papers with code

1 shown of 1 sub-task.

3D Shape Reconstruction From A Single 2D Image

2 benchmarks · 8 papers with code

Shape from Texture

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Image Editing

2 benchmarks · 8 papers with code

Shadow Removal

5 benchmarks · 71 papers with code

Rolling Shutter Correction

1 benchmark · 94 papers with code

Multimodel-guided image editing

0 benchmarks · 4 papers with code

Joint Deblur and Frame Interpolation

0 benchmarks · 1 paper with code

Multimodal fashion image editing

0 benchmarks · 1 paper with code

5 shown of 5 sub-tasks.

Unsupervised Instance Segmentation

2 benchmarks · 8 papers with code

Unsupervised Zero-Shot Instance Segmentation

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Handwriting Verification

2 benchmarks · 6 papers with code

Bangla Spelling Error Correction

1 benchmark · 3 papers with code

1 shown of 1 sub-task.

3D Point Cloud Interpolation

2 benchmarks · 5 papers with code

Point Cloud Registration

24 benchmarks · 229 papers with code

1 shown of 1 sub-task.

Spoof Detection

2 benchmarks · 1 paper with code

Face Presentation Attack Detection

2 benchmarks · 20 papers with code

Detecting Image Manipulation

0 benchmarks · 9 papers with code

Cross-Domain Iris Presentation Attack Detection

0 benchmarks · 3 papers with code

Finger Dorsal Image Spoof Detection

0 benchmarks · 0 papers with code

4 shown of 4 sub-tasks.

Super-Resolution

1 benchmark · 1,627 papers with code

Image Super-Resolution

69 benchmarks · 783 papers with code

Image Rescaling

18 benchmarks · 11 papers with code

Video Super-Resolution

16 benchmarks · 153 papers with code

Reference-based Super-Resolution

1 benchmark · 16 papers with code

Reference-based Video Super-Resolution

1 benchmark · 3 papers with code

5 shown of 7 sub-tasks. All sub-tasks of Super-Resolution →

Active Learning

1 benchmark · 913 papers with code

Active Object Detection

2 benchmarks · 6 papers with code

1 shown of 1 sub-task.

Autonomous Vehicles

1 benchmark · 695 papers with code

Lane Detection

13 benchmarks · 103 papers with code

Traffic Sign Recognition

10 benchmarks · 43 papers with code

Pedestrian Detection

9 benchmarks · 132 papers with code

Pedestrian Attribute Recognition

8 benchmarks · 35 papers with code

Autonomous Driving

4 benchmarks · 2,091 papers with code

5 shown of 15 sub-tasks (1 filed under another area). All sub-tasks of Autonomous Vehicles →

Instruction Following

1 benchmark · 609 papers with code

visual instruction following

1 benchmark · 14 papers with code

1 shown of 1 sub-task.

Explainable Artificial Intelligence (XAI)

1 benchmark · 296 papers with code

Slice Discovery

0 benchmarks · 6 papers with code

1 shown of 1 sub-task.

Video Segmentation

1 benchmark · 160 papers with code

Camera shot boundary detection

4 benchmarks · 7 papers with code

Open-World Video Segmentation

1 benchmark · 1 paper with code

Open-Vocabulary Video Segmentation

0 benchmarks · 2 papers with code

3 shown of 3 sub-tasks.

Camera Pose Estimation

1 benchmark · 134 papers with code

Panorama Pose Estimation (N-view)

1 benchmark · 0 papers with code

1 shown of 1 sub-task.

Visual Odometry

1 benchmark · 124 papers with code

Face Anti-Spoofing

8 benchmarks · 78 papers with code

Monocular Visual Odometry

0 benchmarks · 21 papers with code

2 shown of 2 sub-tasks.

Motion Forecasting

1 benchmark · 88 papers with code

Multi-Person Pose forecasting

2 benchmarks · 7 papers with code

Multiple Object Forecasting

1 benchmark · 1 paper with code

2 shown of 2 sub-tasks.

16k

1 benchmark · 87 papers with code

Object Detection

123 benchmarks · 4,657 papers with code

Image Super-Resolution

69 benchmarks · 783 papers with code

Image Deblurring

9 benchmarks · 167 papers with code

Scene Generation

6 benchmarks · 122 papers with code

Shadow Removal

5 benchmarks · 71 papers with code

5 shown of 6 sub-tasks. All sub-tasks of 16k →

Event-based vision

1 benchmark · 65 papers with code

Event-based Optical Flow

1 benchmark · 14 papers with code

Event-Based Video Reconstruction

1 benchmark · 6 papers with code

Event-based Motion Estimation

0 benchmarks · 6 papers with code

3 shown of 3 sub-tasks.

3D Classification

1 benchmark · 42 papers with code

3D Object Classification

4 benchmarks · 47 papers with code

MRI classification

0 benchmarks · 7 papers with code

2 shown of 2 sub-tasks.

Color Constancy

1 benchmark · 40 papers with code

Few-Shot Camera-Adaptive Color Constancy

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

1 benchmark · 38 papers with code

Vision-Language-Action

0 benchmarks · 49 papers with code

1 shown of 1 sub-task.

Semi-supervised Anomaly Detection

1 benchmark · 37 papers with code

General Action Video Anomaly Detection

1 benchmark · 2 papers with code

Physical Video Anomaly Detection

1 benchmark · 2 papers with code

2 shown of 2 sub-tasks.

Content-Based Image Retrieval

1 benchmark · 34 papers with code

Drone navigation

1 benchmark · 15 papers with code

Drone-view target localization

1 benchmark · 9 papers with code

2 shown of 2 sub-tasks.

Dense Captioning

1 benchmark · 34 papers with code

Live Video Captioning

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Activity Prediction

1 benchmark · 33 papers with code

Sequential skip prediction

1 benchmark · 4 papers with code

motion prediction

0 benchmarks · 234 papers with code

Cyber Attack Detection

0 benchmarks · 6 papers with code

3 shown of 3 sub-tasks (1 filed under another area).

severity prediction

1 benchmark · 29 papers with code

Intubation Support Prediction

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Document AI

1 benchmark · 24 papers with code

document understanding

0 benchmarks · 140 papers with code

1 shown of 1 sub-task.

Inverse-Tone-Mapping

1 benchmark · 21 papers with code

inverse tone mapping

1 benchmark · 17 papers with code

1 shown of 1 sub-task.

One-Shot Segmentation

1 benchmark · 21 papers with code

Patient-Specific Segmentation

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

Value prediction

1 benchmark · 21 papers with code

Body Mass Index (BMI) Prediction

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Room Layout Estimation

1 benchmark · 20 papers with code

Multi-view Floor Layout Reconstruction (N-view)

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Audio-visual Question Answering

1 benchmark · 19 papers with code

AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)

1 benchmark · 5 papers with code

1 shown of 1 sub-task.

inverse tone mapping

1 benchmark · 17 papers with code

Inverse-Tone-Mapping

1 benchmark · 21 papers with code

1 shown of 1 sub-task.

3D Depth Estimation

1 benchmark · 12 papers with code

Transparent Object Depth Estimation

1 benchmark · 4 papers with code

1 shown of 1 sub-task.

Activity Recognition In Videos

1 benchmark · 10 papers with code

Activity Prediction

1 benchmark · 33 papers with code

1 shown of 1 sub-task.

Lung Nodule Classification

1 benchmark · 10 papers with code

Lung Nodule 3D Classification

1 benchmark · 1 paper with code

1 shown of 1 sub-task (1 filed under another area).

Event Segmentation

1 benchmark · 9 papers with code

Generic Event Boundary Detection

2 benchmarks · 12 papers with code

1 shown of 1 sub-task.

Human Instance Segmentation

1 benchmark · 9 papers with code

Pose-Based Human Instance Segmentation

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Situation Recognition

1 benchmark · 9 papers with code

Grounded Situation Recognition

1 benchmark · 11 papers with code

1 shown of 1 sub-task.

Language-Based Temporal Localization

1 benchmark · 6 papers with code

Corpus Video Moment Retrieval

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Lip to Speech Synthesis

1 benchmark · 6 papers with code

Speaker-Specific Lip to Speech Synthesis

7 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Explanatory Visual Question Answering

1 benchmark · 4 papers with code

FS-MEVQA

1 benchmark · 7 papers with code

1 shown of 1 sub-task.

Instance Shadow Detection

1 benchmark · 4 papers with code

Shadow Detection And Removal

0 benchmarks · 7 papers with code

1 shown of 1 sub-task.

Single-Image-Based Hdr Reconstruction

1 benchmark · 4 papers with code

Tone Mapping

0 benchmarks · 43 papers with code

1 shown of 1 sub-task.

1 Image, 2*2 Stitchi

1 benchmark · 3 papers with code

Pose Estimation

31 benchmarks · 1,679 papers with code

Text-to-Image Generation

17 benchmarks · 546 papers with code

Image Deblurring

9 benchmarks · 167 papers with code

Virtual Try-on

9 benchmarks · 114 papers with code

Style Transfer

3 benchmarks · 759 papers with code

5 shown of 12 sub-tasks (3 filed under another area). All sub-tasks of 1 Image, 2*2 Stitchi →

Atomic action recognition

1 benchmark · 3 papers with code

Composite action recognition

1 benchmark · 0 papers with code

1 shown of 1 sub-task.

Object Segmentation

1 benchmark · 3 papers with code

Camouflaged Object Segmentation

7 benchmarks · 38 papers with code

Text-Line Extraction

1 benchmark · 1 paper with code

Landslide segmentation

0 benchmarks · 2 papers with code

3 shown of 3 sub-tasks.

Period Estimation

1 benchmark · 3 papers with code

Art Period Estimation (544 Artists)

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Calving Front Delineation In Synthetic Aperture Radar Imagery

1 benchmark · 2 papers with code

Calving Front Delineation In Synthetic Aperture Radar Imagery With Fixed Training Amount

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Fashion Understanding

1 benchmark · 2 papers with code

Semi-Supervised Fashion Compatibility

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Multi-Oriented Scene Text Detection

1 benchmark · 2 papers with code

Natural Image Orientation Angle Detection

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

2D Semantic Segmentation task 3 (25 classes)

1 benchmark · 1 paper with code

Document Enhancement

0 benchmarks · 8 papers with code

1 shown of 1 sub-task.

Interactive 3D Instance Segmentation

1 benchmark · 1 paper with code

Interactive 3D Instance Segmentation -Trained on Scannet40 - Evaluated on Scannet40

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

LMM real-life tasks

1 benchmark · 1 paper with code

Long Question Answer

0 benchmarks · 1 paper with code

Short Question Answers

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Deep Learning

0 benchmarks · 2,693 papers with code

Polynomial Neural Networks

0 benchmarks · 10 papers with code

1 shown of 1 sub-task.

Video Understanding

0 benchmarks · 542 papers with code

Video Quality Assessment

10 benchmarks · 116 papers with code

Anomaly Detection In Surveillance Videos

7 benchmarks · 44 papers with code

Video Alignment

2 benchmarks · 43 papers with code

Temporal Sentence Grounding

2 benchmarks · 16 papers with code

Causal Discovery in Video Reasoning

1 benchmark · 2 papers with code

5 shown of 7 sub-tasks. All sub-tasks of Video Understanding →

Text to Image Generation

0 benchmarks · 461 papers with code

Text to 3D

1 benchmark · 102 papers with code

1 shown of 1 sub-task.

Explainable artificial intelligence

0 benchmarks · 305 papers with code

Explanation Fidelity Evaluation

6 benchmarks · 6 papers with code

Explainable Models

0 benchmarks · 53 papers with code

FAD Curve Analysis

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

motion prediction

0 benchmarks · 234 papers with code

OPD: Single-view 3D Openable Part Detection

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Neural Rendering

0 benchmarks · 205 papers with code

Neural Radiance Caching

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

0 benchmarks · 195 papers with code

Autonomous Flight (Dense Forest)

1 benchmark · 1 paper with code

Sequential Place Recognition

0 benchmarks · 5 papers with code

Autonomous Web Navigation

0 benchmarks · 4 papers with code

3 shown of 3 sub-tasks.

Simultaneous Localization and Mapping

0 benchmarks · 186 papers with code

Semantic SLAM

2 benchmarks · 19 papers with code

Object SLAM

0 benchmarks · 11 papers with code

2 shown of 2 sub-tasks.

Machine Unlearning

0 benchmarks · 173 papers with code

Continual Forgetting

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

Action Localization

0 benchmarks · 169 papers with code

Temporal Action Localization

14 benchmarks · 493 papers with code

Action Segmentation

9 benchmarks · 99 papers with code

Spatio-Temporal Action Localization

1 benchmark · 14 papers with code

Unusual Activity Localization

0 benchmarks · 1 paper with code

4 shown of 4 sub-tasks.

Face Generation

0 benchmarks · 143 papers with code

Talking Head Generation

7 benchmarks · 51 papers with code

Talking Face Generation

2 benchmarks · 43 papers with code

Facial expression generation

0 benchmarks · 7 papers with code

Face Age Editing

0 benchmarks · 5 papers with code

Kinship face generation

0 benchmarks · 1 paper with code

5 shown of 5 sub-tasks.

document understanding

0 benchmarks · 140 papers with code

Line Items Extraction

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Video Editing

0 benchmarks · 133 papers with code

Video Temporal Consistency

0 benchmarks · 8 papers with code

1 shown of 1 sub-task.

Object Reconstruction

0 benchmarks · 103 papers with code

3D Object Reconstruction

4 benchmarks · 73 papers with code

1 shown of 1 sub-task.

Face Reconstruction

0 benchmarks · 83 papers with code

3D Face Reconstruction

9 benchmarks · 83 papers with code

1 shown of 1 sub-task.

3D Scene Reconstruction

0 benchmarks · 77 papers with code

3D Semantic Scene Completion from a single RGB image

3 benchmarks · 11 papers with code

1 shown of 1 sub-task.

Temporal Localization

0 benchmarks · 76 papers with code

Language-Based Temporal Localization

1 benchmark · 6 papers with code

Temporal Defect Localization

0 benchmarks · 0 papers with code

2 shown of 2 sub-tasks.

MULTI-VIEW LEARNING

0 benchmarks · 75 papers with code

Incomplete multi-view clustering

1 benchmark · 17 papers with code

1 shown of 1 sub-task.

Disease Prediction

0 benchmarks · 73 papers with code

Retinal OCT Disease Classification

2 benchmarks · 10 papers with code

Disease Trajectory Forecasting

1 benchmark · 4 papers with code

2 shown of 2 sub-tasks.

Human motion prediction

0 benchmarks · 68 papers with code

Stochastic Human Motion Prediction

0 benchmarks · 7 papers with code

1 shown of 1 sub-task.

MRI segmentation

0 benchmarks · 68 papers with code

Brain Tumor Classification

1 benchmark · 11 papers with code

1 shown of 1 sub-task.

Physics-informed machine learning

0 benchmarks · 63 papers with code

Soil moisture estimation

0 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Decision Making Under Uncertainty

0 benchmarks · 57 papers with code

Uncertainty Visualization

0 benchmarks · 5 papers with code

1 shown of 1 sub-task.

De-identification

0 benchmarks · 54 papers with code

Privacy Preserving Deep Learning

0 benchmarks · 30 papers with code

Full-body anonymization

0 benchmarks · 4 papers with code

2 shown of 2 sub-tasks.

Open-Vocabulary Semantic Segmentation

0 benchmarks · 54 papers with code

Open-Vocabulary Panoramic Semantic Segmentation

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Indoor Localization

0 benchmarks · 48 papers with code

Indoor Localization (3-DoF Pose: X, Y, Yaw)

2 benchmarks · 1 paper with code

Indoor Localization (6-DoF Pose)

2 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

3D Shape Representation

0 benchmarks · 41 papers with code

3D Dense Shape Correspondence

1 benchmark · 8 papers with code

1 shown of 1 sub-task.

Image to Video Generation

0 benchmarks · 38 papers with code

Open-Domain Subject-to-Video

1 benchmark · 6 papers with code

1 shown of 1 sub-task.

Image Stylization

0 benchmarks · 30 papers with code

One-Shot Face Stylization

0 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Privacy Preserving Deep Learning

0 benchmarks · 30 papers with code

Membership Inference Attack

0 benchmarks · 78 papers with code

Homomorphic Encryption for Deep Learning

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Single Particle Analysis

0 benchmarks · 27 papers with code

2D Particle Picking

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Iris Recognition

0 benchmarks · 26 papers with code

Pupil Dilation

0 benchmarks · 8 papers with code

1 shown of 1 sub-task.

HDR Reconstruction

0 benchmarks · 23 papers with code

Multi-Exposure Image Fusion

0 benchmarks · 17 papers with code

1 shown of 1 sub-task.

Human Dynamics

0 benchmarks · 23 papers with code

3D Human Dynamics

0 benchmarks · 5 papers with code

1 shown of 1 sub-task (1 filed under another area).

Camera Relocalization

0 benchmarks · 22 papers with code

camera absolute pose regression

6 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Grasp Generation

0 benchmarks · 21 papers with code

Controllable Grasp Generation

1 benchmark · 0 papers with code

Grasp rectangle generation

0 benchmarks · 0 papers with code

2 shown of 2 sub-tasks.

0 benchmarks · 19 papers with code

Deblurring

17 benchmarks · 424 papers with code

1 shown of 1 sub-task.

Fake Image Detection

0 benchmarks · 17 papers with code

GAN image forensics

0 benchmarks · 6 papers with code

Fake Image Attribution

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

Class-Incremental Semantic Segmentation

0 benchmarks · 16 papers with code

Overlapped 10-1

2 benchmarks · 10 papers with code

Overlapped 15-1

1 benchmark · 9 papers with code

Overlapped 15-5

1 benchmark · 9 papers with code

Disjoint 15-1

1 benchmark · 7 papers with code

Disjoint 15-5

1 benchmark · 7 papers with code

5 shown of 12 sub-tasks. All sub-tasks of Class-Incremental Semantic Segmentation →

Segmentation Of Remote Sensing Imagery

0 benchmarks · 15 papers with code

Lake Ice Monitoring

0 benchmarks · 6 papers with code

1 shown of 1 sub-task.

Depth And Camera Motion

0 benchmarks · 14 papers with code

Face Anti-Spoofing

8 benchmarks · 78 papers with code

1 shown of 1 sub-task.

Diffusion Personalization

0 benchmarks · 14 papers with code

Diffusion Personalization Tuning Free

1 benchmark · 9 papers with code

Efficient Diffusion Personalization

0 benchmarks · 4 papers with code

2 shown of 2 sub-tasks.

3D Point Cloud Reconstruction

0 benchmarks · 13 papers with code

3D Point Cloud Classification

5 benchmarks · 150 papers with code

1 shown of 1 sub-task.

Deception Detection

0 benchmarks · 12 papers with code

Deception Detection In Videos

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Image Categorization

0 benchmarks · 12 papers with code

Fine-Grained Visual Categorization

0 benchmarks · 31 papers with code

1 shown of 1 sub-task.

Sketch Recognition

0 benchmarks · 12 papers with code

Image to sketch recognition

4 benchmarks · 6 papers with code

1 shown of 1 sub-task.

Interest Point Detection

0 benchmarks · 11 papers with code

Homography Estimation

5 benchmarks · 71 papers with code

1 shown of 1 sub-task.

Indoor Scene Reconstruction

0 benchmarks · 9 papers with code

Plan2Scene

1 benchmark · 1 paper with code

1 shown of 1 sub-task.

Instance Search

0 benchmarks · 9 papers with code

Audio Fingerprint

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Hyperspectral Image Segmentation

0 benchmarks · 8 papers with code

Hyperspectral

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

road scene understanding

0 benchmarks · 8 papers with code

Monocular Cross-View Road Scene Parsing(Road)

3 benchmarks · 2 papers with code

Monocular Cross-View Road Scene Parsing(Vehicle)

2 benchmarks · 2 papers with code

2 shown of 2 sub-tasks.

1 Image, 2*2 Stitching

0 benchmarks · 6 papers with code

Image-to-Image Translation

38 benchmarks · 550 papers with code

Fake Image Detection

0 benchmarks · 17 papers with code

2 shown of 2 sub-tasks.

3D Surface Generation

0 benchmarks · 6 papers with code

Visibility Estimation from Point Cloud

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

ENF (Electric Network Frequency) Extraction

0 benchmarks · 6 papers with code

ENF (Electric Network Frequency) Extraction from Video

0 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Referring Multi-Object Tracking

0 benchmarks · 6 papers with code

Cross-view Referring Multi-Object Tracking

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

3D Shape Reconstruction from Videos

0 benchmarks · 5 papers with code

DeepFake Detection

8 benchmarks · 237 papers with code

1 shown of 1 sub-task.

Landmark Tracking

0 benchmarks · 5 papers with code

Muscle Tendon Junction Identification

2 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Mistake Detection

0 benchmarks · 5 papers with code

Online Mistake Detection

0 benchmarks · 4 papers with code

1 shown of 1 sub-task.

Fine-Grained Vehicle Classification

0 benchmarks · 4 papers with code

Vehicle Color Recognition

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

satellite image super-resolution

0 benchmarks · 4 papers with code

vehicle detection

0 benchmarks · 54 papers with code

1 shown of 1 sub-task.

3D Character Animation From A Single Photo

0 benchmarks · 3 papers with code

Scene Recognition

8 benchmarks · 68 papers with code

1 shown of 1 sub-task.

Referring Image Matting

0 benchmarks · 3 papers with code

Referring Image Matting (Expression-based)

1 benchmark · 3 papers with code

Referring Image Matting (Keyword-based)

1 benchmark · 3 papers with code

Referring Image Matting (RefMatte-RW100)

1 benchmark · 3 papers with code

Referring Image Matting (Prompt-based)

0 benchmarks · 1 paper with code

4 shown of 4 sub-tasks.

Transparent Object Detection

0 benchmarks · 3 papers with code

Transparent objects

0 benchmarks · 37 papers with code

1 shown of 1 sub-task.

3D Mesh Denoising

0 benchmarks · 2 papers with code

3D Noise Generation

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

3D Object Super-Resolution

0 benchmarks · 2 papers with code

Super-Resolution

1 benchmark · 1,627 papers with code

1 shown of 1 sub-task.

Animal Action Recognition

0 benchmarks · 2 papers with code

cow identification

0 benchmarks · 2 papers with code

1 shown of 1 sub-task.

Drawing Pictures

0 benchmarks · 2 papers with code

Style Transfer

3 benchmarks · 759 papers with code

1 shown of 1 sub-task.

Micro-expression Generation

0 benchmarks · 2 papers with code

Micro-expression Generation (MEGC2021)

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Natural Language Transduction

0 benchmarks · 2 papers with code

Lipreading

8 benchmarks · 36 papers with code

1 shown of 1 sub-task.

Part-based Representation Learning

0 benchmarks · 2 papers with code

Unsupervised Part Discovery

0 benchmarks · 4 papers with code

1 shown of 1 sub-task.

Subject-driven Video Generation

0 benchmarks · 2 papers with code

Human Animation

0 benchmarks · 13 papers with code

Audio-Driven Body Animation

0 benchmarks · 1 paper with code

2 shown of 2 sub-tasks.

2D Tiny Object Detection

0 benchmarks · 1 paper with code

Insulator Defect Detection

0 benchmarks · 3 papers with code

1 shown of 1 sub-task.

Brain Visual Reconstruction

0 benchmarks · 1 paper with code

Brain Visual Reconstruction from fMRI

1 benchmark · 2 papers with code

1 shown of 1 sub-task.

Image Instance Retrieval

0 benchmarks · 1 paper with code

Amodal Instance Segmentation

1 benchmark · 15 papers with code

1 shown of 1 sub-task.

Image Recognition

0 benchmarks · 1 paper with code

License Plate Recognition

10 benchmarks · 27 papers with code

Fine-Grained Image Recognition

4 benchmarks · 39 papers with code

Material Recognition

0 benchmarks · 20 papers with code

3 shown of 3 sub-tasks.

Image-based Automatic Meter Reading

0 benchmarks · 1 paper with code

Dial Meter Reading

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Observation Completion

0 benchmarks · 1 paper with code

Active Observation Completion

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Pulmorary Vessel Segmentation

0 benchmarks · 1 paper with code

Pulmonary Artery–Vein Classification

2 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Shape Representation Of 3D Point Clouds

0 benchmarks · 1 paper with code

3D Point Cloud Reconstruction

0 benchmarks · 13 papers with code

1 shown of 1 sub-task.

Sketch

0 benchmarks · 1 paper with code

Face Sketch Synthesis

5 benchmarks · 11 papers with code

Sketch Recognition

0 benchmarks · 12 papers with code

Drawing Pictures

0 benchmarks · 2 papers with code

Photo-To-Caricature Translation

0 benchmarks · 2 papers with code

4 shown of 4 sub-tasks.

2D Classification

0 benchmarks · 0 papers with code

Object Detection

123 benchmarks · 4,657 papers with code

Deblurring

17 benchmarks · 424 papers with code

2D Pose Estimation

9 benchmarks · 46 papers with code

Anomaly Classification

5 benchmarks · 33 papers with code

Cell Detection

4 benchmarks · 60 papers with code

5 shown of 27 sub-tasks (3 filed under another area). All sub-tasks of 2D Classification →

3D

0 benchmarks · 0 papers with code

Object Detection

123 benchmarks · 4,657 papers with code

Pose Estimation

31 benchmarks · 1,679 papers with code

Depth Estimation

14 benchmarks · 1,029 papers with code

3D Reconstruction

10 benchmarks · 793 papers with code

3D Face Reconstruction

9 benchmarks · 83 papers with code

5 shown of 38 sub-tasks (2 filed under another area). All sub-tasks of 3D →

4K 60Fps

0 benchmarks · 0 papers with code

Photo geolocation estimation

6 benchmarks · 13 papers with code

1 shown of 1 sub-task.

Animation

0 benchmarks · 0 papers with code

Image Animation

0 benchmarks · 52 papers with code

3D Character Animation From A Single Photo

0 benchmarks · 3 papers with code

2 shown of 2 sub-tasks.

Cancer

0 benchmarks · 0 papers with code

Breast Cancer Detection

4 benchmarks · 40 papers with code

Lung Cancer Diagnosis

2 benchmarks · 16 papers with code

Breast Cancer Histology Image Classification

2 benchmarks · 12 papers with code

Skin Cancer Classification

1 benchmark · 15 papers with code

Classification Of Breast Cancer Histology Images

0 benchmarks · 5 papers with code

5 shown of 10 sub-tasks. All sub-tasks of Cancer →

Computer Vision Techniques Adopted in 3D Cryogenic Electron Microscopy

0 benchmarks · 0 papers with code

Single Particle Analysis

0 benchmarks · 27 papers with code

Cryogenic Electron Tomography

0 benchmarks · 3 papers with code

2 shown of 2 sub-tasks.

Crowds

0 benchmarks · 0 papers with code

Crowd Counting

13 benchmarks · 154 papers with code

Visual Crowd Analysis

0 benchmarks · 1 paper with code

Group Detection In Crowds

0 benchmarks · 0 papers with code

3 shown of 3 sub-tasks.

Dehazing

0 benchmarks · 0 papers with code

Image Dehazing

15 benchmarks · 157 papers with code

Single Image Dehazing

6 benchmarks · 66 papers with code

2 shown of 2 sub-tasks.

Facial Recognition and Modelling

0 benchmarks · 0 papers with code

Face Alignment

26 benchmarks · 106 papers with code

Face Recognition

25 benchmarks · 639 papers with code

Facial Expression Recognition (FER)

25 benchmarks · 155 papers with code

Face Verification

21 benchmarks · 134 papers with code

Age Estimation

16 benchmarks · 85 papers with code

5 shown of 26 sub-tasks (1 filed under another area). All sub-tasks of Facial Recognition and Modelling →

Forgery

0 benchmarks · 0 papers with code

Localization In Video Forgery

0 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Hand

0 benchmarks · 0 papers with code

Hand Gesture Recognition

18 benchmarks · 53 papers with code

Hand Pose Estimation

10 benchmarks · 103 papers with code

Hand-Gesture Recognition

2 benchmarks · 41 papers with code

Gesture-to-Gesture Translation

2 benchmarks · 6 papers with code

Hand Segmentation

0 benchmarks · 11 papers with code

5 shown of 6 sub-tasks. All sub-tasks of Hand →

Hyperspectral

0 benchmarks · 0 papers with code

Hyperspectral Image Classification

8 benchmarks · 132 papers with code

Hyperspectral Unmixing

0 benchmarks · 30 papers with code

Hyperspectral Image Segmentation

0 benchmarks · 8 papers with code

Classification Of Hyperspectral Images

0 benchmarks · 2 papers with code

4 shown of 4 sub-tasks.

Image Fusion

0 benchmarks · 0 papers with code

Pansharpening

10 benchmarks · 36 papers with code

Multi Focus Image Fusion

0 benchmarks · 19 papers with code

2 shown of 2 sub-tasks.

Intelligent Surveillance

0 benchmarks · 0 papers with code

Vehicle Re-Identification

12 benchmarks · 59 papers with code

1 shown of 1 sub-task.

Remote Sensing

0 benchmarks · 0 papers with code

Extracting Buildings In Remote Sensing Images

3 benchmarks · 10 papers with code

Change detection for remote sensing images

2 benchmarks · 24 papers with code

Building change detection for remote sensing images

2 benchmarks · 19 papers with code

The Semantic Segmentation Of Remote Sensing Imagery

2 benchmarks · 11 papers with code

Remote Sensing Image Classification

1 benchmark · 39 papers with code

5 shown of 8 sub-tasks (1 filed under another area). All sub-tasks of Remote Sensing →

Spectral Estimation

0 benchmarks · 0 papers with code

Spectral Estimation From A Single Rgb Image

0 benchmarks · 0 papers with code

1 shown of 1 sub-task.

Text-To-Image

0 benchmarks · 0 papers with code

Story Visualization

3 benchmarks · 28 papers with code

VGSI

1 benchmark · 1 paper with code

Complex Scene Breaking and Synthesis

0 benchmarks · 1 paper with code

3 shown of 3 sub-tasks.

Video

0 benchmarks · 0 papers with code

Action Classification

28 benchmarks · 251 papers with code

Video Frame Interpolation

21 benchmarks · 114 papers with code

Video Retrieval

19 benchmarks · 255 papers with code

Video Prediction

19 benchmarks · 208 papers with code

Video Generation

16 benchmarks · 609 papers with code

5 shown of 34 sub-tasks. All sub-tasks of Video →

Visual Recognition

0 benchmarks · 0 papers with code

Fine-Grained Visual Recognition

4 benchmarks · 43 papers with code

1 shown of 1 sub-task.

Tasks with no parent task

401 tasks in Computer Vision sit at the top of the archive's task tree with no sub-tasks of their own, most benchmarks first, then most papers with code.

Task tree and counts are the archive's, frozen 2025-07-28 archive 2025-07-28. Nothing here is re-ranked.