CoSTA: End-to-End Comprehensive Space-Time Entanglement for Spatio-Temporal Video Grounding
Yaoyuan Liang, Xiao Liang, Yansong Tang, Zhao Yang, Ziran Li, Jingang Wang, Wenbo Ding, Shao-Lun Huang
Abstract
This paper studies the spatio-temporal video grounding task, which aims to localize a spatio-temporal tube in an untrimmed video based on the given text description of an event. Existing one-stage approaches suffer from insufficient space-time interaction in two aspects: i) less precise prediction of event temporal boundaries, and ii) inconsistency in object prediction for the same event across adjacent frames. To address these issues, we propose a framework of Comprehensive Space-Time entAnglement (CoSTA) to densely entangle space-time multi-modal features for spatio-temporal localization. Specifically, we propose a space-time collaborative encoder to extract comprehensive video features and leverage Transformer to perform spatio-temporal multi-modal understanding. Our entangled decoder couples temporal boundary prediction and spatial localization via an entangled query, boasting an enhanced ability to capture object-event relationships. We conduct extensive experiments on the challenging benchmarks of HC-STVG and VidSTG, where CoSTA outperforms existing state-of-the-art methods, demonstrating its effectiveness for this task.
BibTeX
@article{Liang_Liang_Tang_Yang_Li_Wang_Ding_Huang_2024, title={CoSTA: End-to-End Comprehensive Space-Time Entanglement for Spatio-Temporal Video Grounding}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/28118}, DOI={10.1609/aaai.v38i4.28118}, abstractNote={This paper studies the spatio-temporal video grounding task, which aims to localize a spatio-temporal tube in an untrimmed video based on the given text description of an event. Existing one-stage approaches suffer from insufficient space-time interaction in two aspects: i) less precise prediction of event temporal boundaries, and ii) inconsistency in object prediction for the same event across adjacent frames. To address these issues, we propose a framework of Comprehensive Space-Time entAnglement (CoSTA) to densely entangle space-time multi-modal features for spatio-temporal localization. Specifically, we propose a space-time collaborative encoder to extract comprehensive video features and leverage Transformer to perform spatio-temporal multi-modal understanding. Our entangled decoder couples temporal boundary prediction and spatial localization via an entangled query, boasting an enhanced ability to capture object-event relationships. We conduct extensive experiments on the challenging benchmarks of HC-STVG and VidSTG, where CoSTA outperforms existing state-of-the-art methods, demonstrating its effectiveness for this task.}, number={4}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liang, Yaoyuan and Liang, Xiao and Tang, Yansong and Yang, Zhao and Li, Ziran and Wang, Jingang and Ding, Wenbo and Huang, Shao-Lun}, year={2024}, month={Mar.}, pages={3324-3332} }