TAN: a temporal-aware attention network with context-rich representation for boosting proposal generation

Author:

Jiao Yanyan,Yang Wenzhu,Xing Wenjie,Zeng Shuang,Geng Lei

Abstract

AbstractTemporal action proposal generation in an untrimmed video is very challenging, and comprehensive context exploration is critically important to generate accurate candidates of action instances. This paper proposes a Temporal-aware Attention Network (TAN) that localizes context-rich proposals by enhancing the temporal representations of boundaries and proposals. Firstly, we pinpoint that obtaining precise location information of action instances needs to consider long-distance temporal contexts. To this end, we propose a Global-Aware Attention (GAA) module for boundary-level interaction. Specifically, we introduce two novel gating mechanisms into the top-down interaction structure to incorporate multi-level semantics into video features effectively. Secondly, we design an efficient task-specific Adaptive Temporal Interaction (ATI) module to learn proposal associations. TAN enhances proposal-level contextual representations in a wide range by utilizing multi-scale interaction modules. Extensive experiments on the ActivityNet-1.3 and THUMOS-14 demonstrate the effectiveness of our proposed method, e.g., TAN achieves 73.43% in AR@1000 on THUMOS-14 and 69.01% in AUC on ActivityNet-1.3. Moreover, TAN significantly improves temporal action detection performance when equipped with existing action classification frameworks.

Funder

Important Research Project of Hebei Province

Scientific Research Foundation of Hebei University for Distinguished Young Scholars

Scientific Research Foundation of Colleges and Universities in Hebei Province

Publisher

Springer Science and Business Media LLC

Reference60 articles.

1. Arnab, A., et al., ViViT: A Video Vision Transformer, in IEEE/CVF International Conference on Computer Vision. 2021. p. 6836–6846.

2. Bai Y et al (2020) Boundary content graph neural network for temporal action proposal generation. European Conference on Computer Vision. Springer, pp 121–137

3. Bertasius, G., H. Wang, and L. Torresani, Is Space-Time Attention All You Need for Video Understanding?, in International Conference on Machine Learning. 2021, PMLR. p. 813–824.

4. Bochkovskiy, A., C.-Y. Wang, and H.-Y.M. Liao, Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.

5. Caba Heilbron, F., et al., Activitynet: A large-scale video benchmark for human activity understanding, in IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2015. p. 961–970.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3