Browse State-of-the-Art › Video Object Detection
Video Object Detection
72 papers with code · 7 benchmarks · 13 datasets archive 2025-07-28
Video object detection is the task of detecting objects from a video as opposed to images.
( Image credit: Learning Motion Priors for Efficient Video Object Detection )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
7 leaderboard tables shown for this task (1 more in the archive withheld as spam; see /not-shown), 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| ImageNet VID (33 rows) | YOLOV++ | Practical Video Object Detection via Feature Selection and Aggregation | code | — | Compare |
| EPIC KITCHENS-unseen splits (1 row) | Temporal ROI Align | Temporal RoI Align for Video Object Recognition | code | — | Compare |
| EPIC-KITCHENS-55 (1 row) | Ours (Faster RCNN) | Objects do not disappear: Video object detection by single-frame... | code | — | Compare |
| EPIC KITCHENS-seen splits (1 row) | Temporal ROI Align | Temporal RoI Align for Video Object Recognition | code | — | Compare |
| USC-GRAD-STDdb (1 row) | SLTnet FPN-X101 | Short-term anchor linking and long-term self-guided attention for... | code | — | Compare |
| Waymo Open Dataset (1 row) | (unnamed in the archive) | Objects do not disappear: Video object detection by single-frame... | code | — | Compare |
| YT-BB (1 row) | (unnamed in the archive) | Objects do not disappear: Video object detection by single-frame... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
13 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 147 · with a code link: 72 · where Syntology ran a sample: 12 (11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (12 of 147 tagged: 11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 147, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
29 Apr 2021 32 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified (of 20 harvested samples) · 4 pointer-only (licence)In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).
-
20 Nov 2018 13 repositories listed Syntology official: harvested, nothing ran · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 16 harvested samples) · 6 pointer-only (licence)The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost.
-
13 Jan 2022 3 repositories listed Syntology official (archive's flag): 3 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 3 pointer-only (licence)Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted…
-
14 Apr 2021 3 repositories listedThis paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method.
-
7 Dec 2019 3 repositories listedIn this paper we propose a method that leverages temporal context from the unlabeled frames of a novel camera to improve performance at that camera.
-
30 Nov 2018 3 repositories listed Syntology 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection.
-
16 Apr 2018 3 repositories listedIn this paper, we present a light weight network architecture for video object detection on mobiles.
-
17 Nov 2017 3 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices.
-
4 Feb 2024 2 repositories listedThen, these video prompts are prepended to the patch embeddings of the current frame as the updated input for video feature extraction.
-
9 Aug 2023 2 repositories listed2) Improved efficiency by only doing the expensive feature computations on a small subset of all frames.
-
9 Apr 2020 2 repositories listed Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training.
-
26 Mar 2020 2 repositories listedWe argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information.
-
2 Mar 2020 2 repositories listedAs the tracker reuses the features from the detector, it is a very light-weighted increment to the detection network.
-
16 Jan 2020 2 repositories listedWe provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i. e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking.
-
26 Aug 2019 2 repositories listedIn this paper, we introduce a new design to capture the interactions across the objects in spatio-temporal context.
-
15 Jul 2019 2 repositories listedIn this work, we argue that aggregating features in the full-sequence level will lead to more discriminative and robust features for video object detection.
-
25 Mar 2019 2 repositories listedModels and examples built with TensorFlow
-
29 Mar 2017 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)The accuracy of detection suffers from degenerated object appearances in videos, e. g., motion blur, video defocus, rare poses, etc.
-
11 Aug 2024 1 repository listedFalling objects from buildings can cause severe injuries to pedestrians due to the great impact force they exert.
-
29 Jul 2024 1 repository listedIn principle, the detection in a certain frame of a video can benefit from information in other frames.
-
17 Apr 2024 1 repository listedThis paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors.
-
16 Apr 2024 1 repository listedWe present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques.
-
28 Feb 2024 1 repository listedUrban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes.
-
16 Feb 2024 1 repository listedThe objective of our work is to leverage this complementary information to improve detection.
-
14 Feb 2024 1 repository listedBased on the analysis, we present a simple yet efficient framework to address the computational bottlenecks and achieve efficient one-stage VOD by exploiting the temporal consistency in video frames.
-
14 Feb 2024 1 repository listedDeep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i. e., predicting one result per video.
-
18 Jan 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)However, we argue that these memory structures are not efficient or sufficient because of two implied operations: (1) concatenating all features in memory for enhancement, leading to a heavy computational cost; (2)…
-
30 Oct 2023 1 repository listedTo effectively refine the box from the degraded images in the videos, we used three novel approaches: cascade refinement, dynamic core-set conditioning, and local batch refinement.
-
25 Aug 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 18 unverified (of 25 harvested samples)In this work, we exploit temporal redundancy between subsequent inputs to reduce the cost of Transformers for video processing.
-
22 Aug 2023 1 repository listedThe ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD…
-
15 Aug 2023 1 repository listed
-
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision7 Aug 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result (of 2 harvested samples) · 2 pointer-only (licence)
-
26 Jun 2023 1 repository listed
-
27 Mar 2023 1 repository listed
-
15 Mar 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
26 Dec 2022 1 repository listed
-
24 Nov 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
22 Nov 2022 1 repository listed
-
6 Sep 2022 1 repository listed Syntology official (archive's flag): 14 ran · 14 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified (of 21 harvested samples)
-
20 Aug 2022 1 repository listed
-
17 Jun 2022 1 repository listed
-
28 Apr 2022 1 repository listed
-
17 Mar 2022 1 repository listed
-
17 Nov 2021 1 repository listed
-
18 Sep 2021 1 repository listed
-
15 Sep 2021 1 repository listed
-
8 Sep 2021 1 repository listed
-
12 Aug 2021 1 repository listed
-
23 May 2021 1 repository listed
-
30 Apr 2021 1 repository listed
-
18 Apr 2021 1 repository listed
-
18 Apr 2021 1 repository listed
-
25 Mar 2021 1 repository listed
-
10 Mar 2021 1 repository listed
-
20 Nov 2020 1 repository listed
-
21 Oct 2020 1 repository listed
-
1 Oct 2020 1 repository listed
-
23 Sep 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
3 Apr 2020 1 repository listed
-
24 Mar 2020 1 repository listed
-
2 Mar 2020 1 repository listed
-
13 Nov 2019 1 repository listed
-
18 Aug 2019 1 repository listed
-
6 Jun 2019 1 repository listed
-
5 Jun 2019 1 repository listed
-
28 Mar 2019 1 repository listed
-
16 Apr 2018 1 repository listed
-
18 Dec 2017 1 repository listed
-
2 Aug 2017 1 repository listed
-
Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos25 Jun 2025 0 repositories listed
-
Multimodal Spatio-temporal Graph Learning for Alignment-free RGBT Video Object Detection16 Apr 2025 0 repositories listed
-
Context in object detection: a systematic literature review29 Mar 2025 0 repositories listed
-
Region Masking to Accelerate Video Processing on Neuromorphic Hardware21 Mar 2025 0 repositories listed
-
18 Mar 2025 0 repositories listed
-
Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection6 Dec 2024 0 repositories listed
-
Estimation of Psychosocial Work Environment Exposures Through Video Object Detection. Proof of Concept Using CCTV Footage6 Nov 2024 0 repositories listed
-
Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark16 Oct 2024 0 repositories listed
-
XS-VID: An Extremely Small Video Object Detection Dataset25 Jul 2024 0 repositories listed
-
MaskVD: Region Masking for Efficient Video Object Detection16 Jul 2024 0 repositories listed
-
SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving29 May 2024 0 repositories listed
-
Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions23 Apr 2024 0 repositories listed
-
Towards Enhanced Analysis of Lung Cancer Lesions in EBUS-TBNA -- A Semi-Supervised Video Object Detection Method2 Apr 2024 0 repositories listed
-
7 Feb 2024 0 repositories listed
-
Context Enhanced Transformer for Single Image Object Detection22 Dec 2023 0 repositories listed
-
Traffic Video Object Detection using Motion Prior16 Nov 2023 0 repositories listed
-
Erasure-based Interaction Network for RGBT Video Object Detection and A Unified Benchmark3 Aug 2023 0 repositories listed
-
Deteksi Sampah di Permukaan dan Dalam Perairan pada Objek Video dengan Metode Robust and Efficient Post-Processing dan Tubelet-Level Bounding Box Linking14 Jul 2023 0 repositories listed
-
TransFlow: Transformer as Flow Learner23 Apr 2023 0 repositories listed
-
Memory Maps for Video Object Detection and Tracking on UAVs6 Mar 2023 0 repositories listed
-
Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection20 Dec 2022 0 repositories listed
-
Unifying Tracking and Image-Video Object Detection20 Nov 2022 0 repositories listed
-
Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance10 Nov 2022 0 repositories listed
-
12 Oct 2022 0 repositories listed
-
5 Oct 2022 0 repositories listed
-
DFA: Dynamic Feature Aggregation for Efficient Video Object Detection2 Oct 2022 0 repositories listed
-
1 Sep 2022 0 repositories listed
-
TemporalNet: Real-time 2D-3D Video Object Detection29 Aug 2022 0 repositories listed
Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections