Rethinking the Faster R-CNN Architecture for Temporal Action Localization

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.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Temporal Action Localization THUMOS’14 TAL-Net mAP IOU@0.5 42.8 # 27
mAP IOU@0.1 59.8 # 7
mAP IOU@0.2 57.1 # 5
mAP IOU@0.3 53.2 # 28
mAP IOU@0.4 48.5 # 27
mAP IOU@0.6 33.8 # 23
mAP IOU@0.7 20.8 # 23
Avg mAP (0.3:0.7) 39.8 # 27

Methods