Papers › Cascaded Boundary Regression for Temporal Action Detection

Cascaded Boundary Regression for Temporal Action Detection

2 May 2017arXiv:1705.01180archive 2025-07-28

Jiyang Gao, Zhenheng Yang, Ram Nevatia

Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable portion of the actions, they may not necessarily cover the entire action instance, which would lead to inferior performance. We adapt a two-stage temporal action detection pipeline with Cascaded Boundary Regression (CBR) model. Class-agnostic proposals and specific actions are detected respectively in the first and the second stage. CBR uses temporal coordinate regression to refine the temporal boundaries of the sliding windows. The salient aspect of the refinement process is that, inside each stage, the temporal boundaries are adjusted in a cascaded way by feeding the refined windows back to the system for further boundary refinement. We test CBR on THUMOS-14 and TVSeries, and achieve state-of-the-art performance on both datasets. The performance gain is especially remarkable under high IoU thresholds, e.g. map@tIoU=0.5 on THUMOS-14 is improved from 19.0% to 31.0%.

PaperPDF

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 Detectionregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization THUMOS’14 CBR-TS mAP IOU@0.1 60.1 #34 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 CBR-TS mAP IOU@0.2 56.7 #34 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 CBR-TS mAP IOU@0.3 50.1 #34 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 CBR-TS mAP IOU@0.4 41.3 #34 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 CBR-TS mAP IOU@0.5 31 #34 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 CBR-TS mAP IOU@0.6 19.1 #34 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 CBR-TS mAP IOU@0.7 9.9 #34 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