Papers › Finding Action Tubes

Finding Action Tubes

21 Nov 2014CVPR 2015 6arXiv:1411.6031archive 2025-07-28

Georgia Gkioxari, Jitendra Malik

We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance and motion in two ways. First, starting from image region proposals we select those that are motion salient and thus are more likely to contain the action. This leads to a significant reduction in the number of regions being processed and allows for faster computations. Second, we extract spatio-temporal feature representations to build strong classifiers using Convolutional Neural Networks. We link our predictions to produce detections consistent in time, which we call action tubes. We show that our approach outperforms other techniques in the task of action detection.

PaperPDFConference PDFCode

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

Code

JeffCHEN2017/WSSTG mentioned on GitHubpytorchNOASSERTION 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 DetectionObject DetectionSkeleton Based Action Recognitionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection J-HMDB Action Tubes Frame-mAP 0.5 36.2 #13 of 18 Archive leaderboard report
Action Detection J-HMDB Action Tubes Video-mAP 0.5 53.3 #13 of 18 Archive leaderboard report
Action Detection UCF Sports Action Tubes Frame-mAP 0.5 68.1 #4 of 7 Archive leaderboard report
Action Detection UCF Sports Action Tubes Video-mAP 0.5 75.8 #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition J-HMDB Action Tubes Accuracy (RGB+pose) 62.5 #10 of 13 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