-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shi_2023_CVPR, author = {Shi, Dingfeng and Zhong, Yujie and Cao, Qiong and Ma, Lin and Li, Jia and Tao, Dacheng}, title = {TriDet: Temporal Action Detection With Relative Boundary Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18857-18866} }
TriDet: Temporal Action Detection With Relative Boundary Modeling
Abstract
In this paper, we present a one-stage framework TriDet for temporal action detection. Existing methods often suffer from imprecise boundary predictions due to the ambiguous action boundaries in videos. To alleviate this problem, we propose a novel Trident-head to model the action boundary via an estimated relative probability distribution around the boundary. In the feature pyramid of TriDet, we propose a Scalable-Granularity Perception (SGP) layer to aggregate information across different temporal granularities, which is much more efficient than the recent transformer-based feature pyramid. Benefiting from the Trident-head and the SGP-based feature pyramid, TriDet achieves state-of-the-art performance on three challenging benchmarks: THUMOS14, HACS and EPIC-KITCHEN 100, with lower computational costs, compared to previous methods. For example, TriDet hits an average mAP of 69.3% on THUMOS14, outperforming the previous best by 2.5%, but with only 74.6% of its latency.
Related Material