ELAN: Enhancing Temporal Action Detection with Location Awareness
Lists
Only you see this
Abstract
Current query-based temporal action detection methods lack multiple levels of location awareness, leading to performance degradation. In this paper, we present a novel query-based method called Enhanced Location-Aware Network (ELAN) for temporal action detection. ELAN adopts a lightweight convolution-based encoder, termed Temporal Location-Aware (TLA) encoder, to model temporal continuous location-aware context. Moreover, ELAN can re-aware the location-related context inside and between queries through our proposed Instance Location-Aware (ILA) decoder. As a result, ELAN can learn strong position discrimination of actions and effectively eliminates the ambiguity caused by sparse action decoding, yielding significant improvement in detection performance. ELAN achieves state-of-the-art performance on two temporal action detection benchmarks, including THUMOS-14 and ActivityNet-1.3.
BibTeX
@inproceedings{chen2023elan,
author = {Guo Chen and Yin-Dong Zheng and Zhe Chen and Jiahao Wang and Tong Lu},
title = {{ELAN: Enhancing Temporal Action Detection with Location Awareness}},
booktitle = {ICME},
year = {2023},
url = {https://openreview.net/forum?id=JZrCOqbf5i},
}Loading related content...