Papers › TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Jiyang Gao, Zhenheng Yang, Chen Sun, Kan Chen, Ram Nevatia
Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression; (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the state-of-the-art methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms state-of-the-art performance on THUMOS-14 and ActivityNet.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Recognition | THUMOS’14 | TURN | mAP@0.3 | 46.3 | #8 of 10 | Archive leaderboard | report |
| Action Recognition | THUMOS’14 | TURN | mAP@0.4 | 35.3 | #8 of 10 | Archive leaderboard | report |
| Action Recognition | THUMOS’14 | TURN | mAP@0.5 | 24.5 | #8 of 10 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | TURN-FL-16 + S-CNN | mAP IOU@0.1 | 54 | #36 of 42 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | TURN-FL-16 + S-CNN | mAP IOU@0.2 | 50.9 | #36 of 42 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | TURN-FL-16 + S-CNN | mAP IOU@0.3 | 44.1 | #36 of 42 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | TURN-FL-16 + S-CNN | mAP IOU@0.4 | 34.9 | #36 of 42 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | TURN-FL-16 + S-CNN | mAP IOU@0.5 | 25.6 | #36 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