Papers › Rethinking the Faster R-CNN Architecture for Temporal Action Localization

Rethinking the Faster R-CNN Architecture for Temporal Action Localization

20 Apr 2018CVPR 2018 6arXiv:1804.07667archive 2025-07-28

Yu-Wei Chao, Sudheendra Vijayanarasimhan, Bryan Seybold, David A. Ross, Jia Deng, Rahul Sukthankar

We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we improve receptive field alignment using a multi-scale architecture that can accommodate extreme variation in action durations; (2) we better exploit the temporal context of actions for both proposal generation and action classification by appropriately extending receptive fields; and (3) we explicitly consider multi-stream feature fusion and demonstrate that fusing motion late is important. We achieve state-of-the-art performance for both action proposal and localization on THUMOS'14 detection benchmark and competitive performance on ActivityNet challenge.

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 ClassificationAction LocalizationGeneral ClassificationObject DetectionTemporal Action Localizationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization THUMOS’14 TAL-Net Avg mAP (0.3:0.7) 39.8 #29 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.1 59.8 #29 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.2 57.1 #29 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.3 53.2 #29 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.4 48.5 #29 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.5 42.8 #29 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.6 33.8 #29 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.7 20.8 #29 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.

Methods

ConvolutionFaster R-CNNRPNRoIPoolSoftmax

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