Papers › RGB Stream Is Enough for Temporal Action Detection

RGB Stream Is Enough for Temporal Action Detection

9 Jul 2021arXiv:2107.04362archive 2025-07-28

Chenhao Wang, Hongxiang Cai, Yuxin Zou, Yichao Xiong

State-of-the-art temporal action detectors to date are based on two-stream input including RGB frames and optical flow. Although combining RGB frames and optical flow boosts performance significantly, optical flow is a hand-designed representation which not only requires heavy computation, but also makes it methodologically unsatisfactory that two-stream methods are often not learned end-to-end jointly with the flow. In this paper, we argue that optical flow is dispensable in high-accuracy temporal action detection and image level data augmentation (ILDA) is the key solution to avoid performance degradation when optical flow is removed. To evaluate the effectiveness of ILDA, we design a simple yet efficient one-stage temporal action detector based on single RGB stream named DaoTAD. Our results show that when trained with ILDA, DaoTAD has comparable accuracy with all existing state-of-the-art two-stream detectors while surpassing the inference speed of previous methods by a large margin and the inference speed is astounding 6668 fps on GeForce GTX 1080 Ti. Code is available at \url{https://github.com/Media-Smart/vedatad}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Media-Smart/vedatad officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action DetectionData AugmentationOptical Flow EstimationTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization THUMOS’14 DaoTAD Avg mAP (0.3:0.7) 50.0 #27 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DaoTAD mAP IOU@0.3 62.8 #27 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DaoTAD mAP IOU@0.4 59.5 #27 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DaoTAD mAP IOU@0.5 53.8 #27 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DaoTAD mAP IOU@0.6 43.6 #27 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DaoTAD mAP IOU@0.7 30.1 #27 of 42 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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