Methods › Computer Vision

Computer Vision

875 methods 117 collections 52,857 papers tagged archive 2025-07-28

Collections are ordered by tagged papers; each shows its 5 most-tagged methods.

Convolutions

43 methods · 20,128 papers

Convolution

19,586 papers

1x1 Convolution

5,640 papers

Depthwise Convolution

1,321 papers

Pointwise Convolution

1,306 papers

5 shown of 43 methods →

Image Generation Models

12 methods · 13,867 papers

Diffusion

13,848 papers

GLIDE

Guided Language to Image Diffusion for Generation and Editing

28 papers

5 shown of 12 methods →

Pooling Operations

17 methods · 8,860 papers

Max Pooling

7,126 papers

Average Pooling

5,125 papers

Global Average Pooling

4,076 papers

5 shown of 17 methods →

Vision and Language Pre-Trained Models

30 methods · 8,661 papers

ALIGN

5,527 papers

CLIP

Contrastive Language-Image Pre-training

3,094 papers

BLIP

BLIP: Bootstrapping Language-Image Pre-training

93 papers

LXMERT

Learning Cross-Modality Encoder Representations from Transformers

40 papers

OSCAR

36 papers

5 shown of 30 methods →

Image Model Blocks

83 methods · 4,655 papers

Residual Block

2,807 papers

Dense Block

497 papers

Inception Module

206 papers

5 shown of 83 methods →

Image Models

33 methods · 3,998 papers

Vision Transformer

2,144 papers

Interpretability

1,322 papers

EfficientNet

195 papers

MLP-Mixer

96 papers

DeiT

Data-efficient Image Transformer

93 papers

5 shown of 33 methods →

Semantic Segmentation Models

33 methods · 3,265 papers

U-Net

2,588 papers

FCN

Fully Convolutional Network

285 papers

SegNet

81 papers

UNet++

61 papers

DeepLab

55 papers

5 shown of 33 methods →

Image Representations

11 methods · 3,214 papers

CLIP

Contrastive Language-Image Pre-training

3,094 papers

Laplacian Pyramid

31 papers

Bilateral Grid

11 papers

5 shown of 11 methods →

Vision Transformers

42 methods · 2,733 papers

Vision Transformer

2,144 papers

Swin Transformer

416 papers

DINO

self-DIstillation with NO labels

208 papers

NesT

37 papers

Deformable DETR

35 papers

5 shown of 42 methods →

Object Detection Models

63 methods · 2,318 papers

Faster R-CNN

499 papers

Mask R-CNN

420 papers

SSD

278 papers

YOLOv3

258 papers

YOLOv8

You Only Look Once

254 papers

5 shown of 63 methods →

Image Data Augmentation

38 methods · 2,220 papers

GPS

Greedy Policy Search

707 papers

Mixup

651 papers

Random Resized Crop

303 papers

ColorJitter

Color Jitter

260 papers

5 shown of 38 methods →

Generative Models

63 methods · 1,913 papers

StyleGAN

292 papers

VQ-VAE

197 papers

Pix2Pix

132 papers

5 shown of 63 methods →

Convolutional Neural Networks

112 methods · 1,807 papers

CapsNet

Capsule Network

202 papers

3D CNN

3 Dimensional Convolutional Neural Network

178 papers

CSPDarknet53

132 papers

ResNeXt

132 papers

GoogLeNet

122 papers

5 shown of 112 methods →

Image Denoising Models

5 methods · 1,328 papers

PCA

Principal Components Analysis

1,323 papers

Noise2Fast

2 papers

DU-GAN

1 paper

JDeskew

Adaptive Radial Projection on Fourier Magnitude Spectrum

1 paper

RoI Feature Extractors

12 methods · 1,126 papers

RoIPool

620 papers

RoIAlign

611 papers

5 shown of 12 methods →

Region Proposal

5 methods · 1,090 papers

RPN

Region Proposal Network

1,045 papers

Selective Search

23 papers

CAG

Class activation guide

18 papers

DeepMask

6 papers

EdgeBoxes

2 papers

Feature Extractors

25 methods · 1,067 papers

FPN

Feature Pyramid Network

583 papers

TS

Spatio-temporal stability analysis

242 papers

PAFPN

124 papers

DLA

Deep Layer Aggregation

94 papers

5 shown of 25 methods →

Image Segmentation Models

9 methods · 926 papers

SAM

Segment Anything Model

905 papers

DEXTR

Deep Extreme Cut

5 papers

HANet

Height-driven Attention Network

5 papers

BCA-Segmentation

Segmentation of patchy areas in biomedical images based on local edge density estimation

3 papers

pGAN

Parallel GAN

3 papers

5 shown of 9 methods →

One-Stage Object Detection Models

21 methods · 919 papers

SSD

278 papers

YOLOv3

258 papers

RetinaNet

209 papers

YOLOv4

100 papers

FCOS

80 papers

5 shown of 21 methods →

Instance Segmentation Models

15 methods · 526 papers

Mask R-CNN

420 papers

HTC

Hybrid Task Cascade

46 papers

Cascade Mask R-CNN

23 papers

PANet

18 papers

CPN

Contour Proposal Network

14 papers

5 shown of 15 methods →

Generative Adversarial Networks

35 methods · 455 papers

SAGAN

Self-Attention GAN

138 papers

BigGAN

103 papers

WGAN

Wasserstein GAN

95 papers

StyleGAN2

49 papers

InfoGAN

35 papers

5 shown of 35 methods →

Proposal Filtering

7 methods · 420 papers

Soft-NMS

22 papers

Matrix NMS

Matrix Non-Maximum Suppression

5 papers

Adaptive NMS

3 papers

DIoU-NMS

2 papers

5 shown of 7 methods →

3D Face Mesh Models

2 methods · 391 papers

Repair

384 papers

VQ-VAE-2

7 papers

Likelihood-Based Generative Models

7 methods · 310 papers

VQ-VAE

197 papers

PixelCNN

45 papers

Beta-VAE

30 papers

NICE

Non-linear Independent Component Estimation

22 papers

RealNVP

19 papers

5 shown of 7 methods →

Light-weight neural networks

16 methods · 307 papers

SqueezeNet

97 papers

MobileNetV1

74 papers

ShuffleNet

51 papers

ESPNet

23 papers

GhostNet

22 papers

5 shown of 16 methods →

Feature Pyramid Blocks

10 methods · 248 papers

PAFPN

124 papers

BiFPN

48 papers

Attention Pooling

46 papers

NAS-FPN

11 papers

RFP

Recursive Feature Pyramid

10 papers

5 shown of 10 methods →

Backbone Architectures

10 methods · 243 papers

ConvNeXt

165 papers

Deep Sets

35 papers

TNT

Transformer in Transformer

12 papers

FFF

Fast Feedforward Networks

6 papers

5 shown of 10 methods →

Image Feature Extractors

4 methods · 191 papers

Non-Local Operation

181 papers

Involution

5 papers

Hamburger

2 papers

Semantic Segmentation Modules

12 methods · 187 papers

ASPP

Atrous Spatial Pyramid Pooling

83 papers

PointRend

9 papers

5 shown of 12 methods →

Downsampling

2 methods · 160 papers

SMOTE

Synthetic Minority Over-sampling Technique.

156 papers

Localization Models

3 methods · 159 papers

Fragmentation

123 papers

ORB-SLAM2

ORB-Simultaneous localization and mapping

33 papers

IoU-Net

3 papers

Video Object Segmentation Models

3 methods · 118 papers

VOS

117 papers

MiVOS

Modular Interactive VOS

1 paper

Object Detection Modules

1 method · 102 papers

Grid Sensitive

102 papers

Multi-Object Tracking Models

10 methods · 90 papers

Wizard

Wizard: Unsupervised goats tracking algorithm

64 papers

CenterTrack

Track objects as points

11 papers

FairMOT

7 papers

LMOT

LMOT: Efficient Light-Weight Detection and Tracking in Crowds

2 papers

SMOT

Single-Shot Multi-Object Tracker

2 papers

5 shown of 10 methods →

Pose Estimation Models

7 methods · 82 papers

OpenPose

48 papers

ZoomNet

3 papers

BADGR

Bundle Adjustment Diffusion Conditioned by Gradients

1 paper

FCPose

1 paper

5 shown of 7 methods →

Degridding

1 method · 64 papers

Generative Training

4 methods · 60 papers

ILVR

Iterative Latent Variable Refinement

1 paper

Safety-llamas

1 paper

Multi-Modal Methods

11 methods · 53 papers

GLIDE

Guided Language to Image Diffusion for Generation and Editing

28 papers

EmbraceNet

EmbraceNet: A robust deep learning architecture for multimodal classification

4 papers

MAVL

Multiscale Attention ViT with Late fusion

4 papers

UNIMO

4 papers

VATT

3 papers

5 shown of 11 methods →

Video Model Blocks

6 methods · 53 papers

CRN

Conditional Relation Network

44 papers

IFBlock

6 papers

Sscs

Support-set Based Cross-Supervision

1 paper

5 shown of 6 methods →

Medical Image Models

3 methods · 51 papers

UNETR

UNet Transformer

49 papers

BS-Net

1 paper

Co-Correcting

1 paper

Conditional Image-to-Image Translation Models

1 method · 50 papers

OASIS

50 papers

Face Recognition Models

6 methods · 42 papers

MFR

Meta Face Recognition

19 papers

NFR

Negative Face Recognition

10 papers

MagFace

7 papers

CurricularFace

3 papers

PocketNet

2 papers

5 shown of 6 methods →

Arbitrary Object Detectors

1 method · 38 papers

CSL

Circular Smooth Label

38 papers

3D Reconstruction

5 methods · 29 papers

ARCH

Animatable Reconstruction of Clothed Humans

23 papers

CodeSLAM

2 papers

MonoPort

Monocular Real-Time Volumetric Performance Capture

2 papers

NeuralRecon

NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video

2 papers

Generative Video Models

7 methods · 27 papers

TimeSformer

18 papers

CVRL

Contrastive Video Representation Learning

3 papers

Dreamix

Dreamix: video diffusion models are general video editors

2 papers

ClipBERT

1 paper

DVD-GAN

1 paper

5 shown of 7 methods →

Image Restoration Models

4 methods · 27 papers

NAFNet

Nonlinear Activation Free Network

13 papers

TLC

Test-time Local Converter

10 papers

MPRNet

3 papers

Conffusion

Confidence Intervals for Diffusion Models

1 paper

Image Quality Models

2 methods · 24 papers

DKL

Deep Kernel Learning

20 papers

MUSIQ

4 papers

Multi-Scale Training

2 methods · 21 papers

SNIP

17 papers

SNIPER

5 papers

Stereo Depth Estimation Models

3 methods · 19 papers

Spatial Propagation

Surface Nomral-based Spatial Propagation

16 papers

Bi3D

2 papers

HITNet

1 paper

Image Retrieval Models

3 methods · 16 papers

RFE

Rank Flow Embedding

13 papers

DELG

2 papers

DOLG

Deep Orthogonal Fusion of Local and Global Features

1 paper

Whitening

2 methods · 15 papers

ZCA Whitening

10 papers

PCA Whitening

6 papers

OCR Models

2 methods · 14 papers

TrOCR

11 papers

PP-OCR

4 papers

Point Cloud Models

7 methods · 12 papers

YOHO

You Only Hypothesize Once

4 papers

PREDATOR

2 papers

RPM-Net

2 papers

PQ-Transformer

PointQuad-Transformer

1 paper

5 shown of 7 methods →

Action Recognition Models

3 methods · 11 papers

TDN

Temporaral Difference Network

8 papers

HalluciNet

Approximating Spatiotemporal Representations Using a 2DCNN

1 paper

Image Scaling Strategies

1 method · 10 papers

FixRes

10 papers

Feature Upsampling

3 methods · 9 papers

CARAFE

6 papers

IndexNet

Index Networks

2 papers

A2U

Affinity-Aware Upsampling

1 paper

Pose Estimation Blocks

2 methods · 9 papers

KPE

Keypoint Pose Encoding

7 papers

ORN

Orientation Regularized Network

2 papers

Video-Text Retrieval Models

4 methods · 9 papers

CoVR

Composed Video Retrieval

4 papers

CAMoE

2 papers

VLG-Net

Video Language Graph Matching Network

2 papers

ReGaDa

Residual gating mechanism to compose adverb-action representations

1 paper

3D Object Detection Models

6 methods · 8 papers

CT3D

2 papers

I3DR-Net

Inflated 3D ConvNet Retina Net

2 papers

3DSSD

1 paper

Disp R-CNN

1 paper

Point-GNN

1 paper

5 shown of 6 methods →

Adversarial Image Data Augmentation

3 methods · 8 papers

DiffAugment

3 papers

MaxUp

2 papers

Face Restoration Models

5 methods · 8 papers

GFP-GAN

3 papers

ISPL

Implicit Subspace Prior Learning

3 papers

DFDNet

1 paper

PSFR-GAN

1 paper

WIPA

Wavelet-integrated Identity Preserving Adversarial Network for face super-resolution

0 papers

Point Cloud Representations

2 methods · 8 papers

PolarNet

6 papers

BTF

Back to the Feature

2 papers

Scene Text Models

3 methods · 8 papers

ABCNet

Adaptive Bezier-Curve Network

3 papers

PGNet

Point Gathering Network

2 papers

Mask Branches

1 method · 7 papers

Video Recognition Models

4 methods · 7 papers

3D ResNet-RS

3 papers

MoViNet

2 papers

AVSlowFast

Audiovisual SlowFast Network

1 paper

Dual-Stream C3D

1 paper

3D Representations

5 methods · 6 papers

StereoLayers

2 papers

DeltaConv

1 paper

LSDM

Language-driven Scene Synthesis using Multi-conditional Diffusion Model

1 paper

Models Genesis

1 paper

imGHUM

1 paper

Cashier-Free Shopping

1 method · 6 papers

Grab

6 papers

Face Privacy

2 methods · 6 papers

Fawkes

5 papers

PrivacyNet

1 paper

Image Super-Resolution Models

2 methods · 6 papers

PULSE

5 papers

ClassSR

1 paper

Instance Segmentation Modules

3 methods · 6 papers

PolarMask

3 papers

bilayer decoupling

bilayer convolutional neural network

2 papers

Video Frame Interpolation

2 methods · 6 papers

IFNet

6 papers

RIFE

2 papers

Counting Methods

2 methods · 5 papers

EBC

Enhanced Blockwise Classification

4 papers

Explainable CNNs

2 methods · 5 papers

XGrad-CAM

3 papers

PolyCAM

Poly-CAM

2 papers

Generative Discrimination

1 method · 5 papers

Portrait Matting Models

2 methods · 5 papers

MODNet

4 papers

STATEGAME MAINTAIN PICTURE BALANCED PLAY STABLE

ATTEMPT THIS FATHINETUTE TO REPOPULATE ALREADY POPULATED SYSTEM

1 paper

Trajectory Prediction Models

2 methods · 5 papers

Social-STGCNN

4 papers

OOSTraj

Out-of-Sight Trajectory Prediction

1 paper

Unpaired Image-to-Image Translation

3 methods · 5 papers

ALDA

2 papers

COCO-FUNIT

1 paper

Video Sampling

1 method · 5 papers

Video Super-Resolution Models

1 method · 5 papers

BasicVSR

5 papers

6D Pose Estimation Models

4 methods · 4 papers

ARShoe

1 paper

FFB6D

1 paper

PO3D-VQA

Parts, Poses, and Occlusions in 3D Visual Question Answering

1 paper

PixLoc

1 paper

Anchor Generation Modules

2 methods · 4 papers

Guided Anchoring

3 papers

Style Transfer Modules

2 methods · 4 papers

Revision Network

4 papers

Drafting Network

2 papers

Trajectory Data Augmentation

1 method · 4 papers

SimAug

Simulation as Augmentation

4 papers

Anchor Supervision

1 method · 3 papers

FreeAnchor

3 papers

Reversible Image Conversion Models

2 methods · 3 papers

IICNet

2 papers

RevSilo

1 paper

Video Data Augmentation

1 method · 3 papers

Video Instance Segmentation Models

1 method · 3 papers

VisTR

3 papers

Video Quality Models

1 method · 3 papers

MDTVSFA

3 papers

Face Detection Models

1 method · 2 papers

TinaFace

2 papers

Lane Detection Models

1 method · 2 papers

YOLOP

2 papers

Math Formula Detection Models

1 method · 2 papers

LLM-SR

Symbolic Regression Large Language Models

2 papers

Meshing

1 method · 2 papers

NeuralRecon

NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video

2 papers

Motion Prediction Models

1 method · 2 papers

MotionNet

2 papers

Person Search Models

1 method · 2 papers

AlignPS

Feature-Aligned Person Search Network

2 papers

Style Transfer Models

1 method · 2 papers

LapStyle

Laplacian Pyramid Network

2 papers

VQA Models

3 methods · 2 papers

HYDRA (VL4AI)

A Hyper Agent for Dynamic Compositional Visual Reasoning

1 paper

MODERN

Modulated Residual Network

1 paper

U-CAM

Uncertainty Class Activation Map (U-CAM) Using Gradient Certainty Method

0 papers

Video Interpolation Models

1 method · 2 papers

FLAVR

2 papers

Video Panoptic Segmentation Models

2 methods · 2 papers

VPSNet

Video Panoptic Segmentation Network

1 paper

ViP-DeepLab

1 paper

Webpage Object Detection Pipeline

1 method · 2 papers

CoVA

Context-aware Visual Attention-based (CoVA) webpage object detection pipeline

2 papers

CAD Design Models

1 method · 1 paper

BRepNet

1 paper

Deraining Models

1 method · 1 paper

MSPFN

Multi-scale Progressive Fusion Network

1 paper

Detection Assignment Rules

1 method · 1 paper

POTO

Prediction-aware One-To-One

1 paper

Few-Shot Image-to-Image Translation

1 method · 1 paper

COCO-FUNIT

1 paper

Font Generation Models

1 method · 1 paper

Attribute2Font

1 paper

Human Object Interaction Detectors

1 method · 1 paper

VSGNet

Visual-Spatial-Graph Network

1 paper

Image Colorization Models

1 method · 1 paper

Image Decomposition Models

1 method · 1 paper

BIDeN

Blind Image Decomposition Network

1 paper

Image Inpainting Modules

1 method · 1 paper

Image Semantic Segmentation Metric

1 method · 1 paper

IPBI

Instances-Pixels Balance Index

1 paper

Layout Annotation Models

1 method · 1 paper

BoundaryNet

1 paper

Output Heads

1 method · 1 paper

Point Cloud Augmentation

2 methods · 1 paper

PointAugment

1 paper

PatchAugment

PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification

0 papers

RGB-D Saliency Detection Models

1 method · 1 paper

UCNet

1 paper

Rendezvous

1 method · 1 paper

MHMA

Multi-Heads of Mixed Attention

1 paper

Text Instance Representations

1 method · 1 paper

Thermal Image Processing Models

1 method · 1 paper

DeepIR

1 paper

Graphics Models

1 method · 0 papers

ManifoldPlus

0 papers