Papers › Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos

Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos

30 Mar 2017ICCV 2017 10arXiv:1703.10664archive 2025-07-28

Rui Hou, Chen Chen, Mubarak Shah

Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis (e.g. action detection and recognition) has been limited due to complexity of video data and lack of annotations. Previous convolutional neural networks (CNN) based video action detection approaches usually consist of two major steps: frame-level action proposal detection and association of proposals across frames. Also, these methods employ two-stream CNN framework to handle spatial and temporal feature separately. In this paper, we propose an end-to-end deep network called Tube Convolutional Neural Network (T-CNN) for action detection in videos. The proposed architecture is a unified network that is able to recognize and localize action based on 3D convolution features. A video is first divided into equal length clips and for each clip a set of tube proposals are generated next based on 3D Convolutional Network (ConvNet) features. Finally, the tube proposals of different clips are linked together employing network flow and spatio-temporal action detection is performed using these linked video proposals. Extensive experiments on several video datasets demonstrate the superior performance of T-CNN for classifying and localizing actions in both trimmed and untrimmed videos compared to state-of-the-arts.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

cyberpunk317/Action_detection mentioned on GitHubpytorch 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 DetectionImage ClassificationObject DetectionVideo Action Detectionimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection J-HMDB T-CNN Frame-mAP 0.5 61.3 #9 of 18 Archive leaderboard report
Action Detection J-HMDB T-CNN Video-mAP 0.2 78.4 #9 of 18 Archive leaderboard report
Action Detection J-HMDB T-CNN Video-mAP 0.5 76.9 #9 of 18 Archive leaderboard report
Action Detection UCF Sports T-CNN Frame-mAP 0.5 86.7 #1 of 7 Archive leaderboard report
Action Detection UCF101-24 T-CNN Frame-mAP 0.5 41.37 #13 of 19 Archive leaderboard report
Action Detection UCF101-24 T-CNN Video-mAP 0.1 51.3 #13 of 19 Archive leaderboard report
Action Detection UCF101-24 T-CNN Video-mAP 0.2 47.1 #13 of 19 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.

Methods

3D ConvolutionConvolution

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