Papers › TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection

TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection

31 May 2019CVPR 2019 6arXiv:1905.13417archive 2025-07-28

Lin Song, Shiwei Zhang, Gang Yu, Hongbin Sun

Current state-of-the-art approaches for spatio-temporal action detection have achieved impressive results but remain unsatisfactory for temporal extent detection. The main reason comes from that, there are some ambiguous states similar to the real actions which may be treated as target actions even by a well-trained network. In this paper, we define these ambiguous samples as "transitional states", and propose a Transition-Aware Context Network (TACNet) to distinguish transitional states. The proposed TACNet includes two main components, i.e., temporal context detector and transition-aware classifier. The temporal context detector can extract long-term context information with constant time complexity by constructing a recurrent network. The transition-aware classifier can further distinguish transitional states by classifying action and transitional states simultaneously. Therefore, the proposed TACNet can substantially improve the performance of spatio-temporal action detection. We extensively evaluate the proposed TACNet on UCF101-24 and J-HMDB datasets. The experimental results demonstrate that TACNet obtains competitive performance on JHMDB and significantly outperforms the state-of-the-art methods on the untrimmed UCF101-24 in terms of both frame-mAP and video-mAP.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Action Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection J-HMDB TACNet Frame-mAP 0.5 65.5 #8 of 18 Archive leaderboard report
Action Detection J-HMDB TACNet Video-mAP 0.2 74.1 #8 of 18 Archive leaderboard report
Action Detection J-HMDB TACNet Video-mAP 0.5 73.4 #8 of 18 Archive leaderboard report
Action Detection UCF101-24 TACNet Frame-mAP 0.5 72.1 #11 of 19 Archive leaderboard report
Action Detection UCF101-24 TACNet Video-mAP 0.2 77.5 #11 of 19 Archive leaderboard report
Action Detection UCF101-24 TACNet Video-mAP 0.5 52.9 #11 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.

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