Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding

Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, Zeyu Xiong


Abstract
Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then interact them with query for reasoning.However, we argue that these methods have overlooked two indispensable issues:1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries.2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model.To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding.Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets.
Anthology ID:
2022.findings-emnlp.41
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
590–600
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.41
DOI:
10.18653/v1/2022.findings-emnlp.41
Bibkey:
Cite (ACL):
Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, and Zeyu Xiong. 2022. Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 590–600, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding (Zhu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.41.pdf