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.
@article{arxiv.1804.07667,
title = {Rethinking the Faster R-CNN Architecture for Temporal Action Localization},
author = {Yu-Wei Chao and Sudheendra Vijayanarasimhan and Bryan Seybold and David A. Ross and Jia Deng and Rahul Sukthankar},
journal= {arXiv preprint arXiv:1804.07667},
year = {2018}
}