Mitigating the Discrepancy Between Video and Text Temporal Sequences: A Time-Perception Enhanced Video Grounding method for LLM

Xuefen Li, Bo Wang, Ge Shi, Chong Feng, Jiahao Teng


Abstract
Existing video LLMs typically excel at capturing the overall description of a video but lack the ability to demonstrate an understanding of temporal dynamics and a fine-grained grasp of localized content within the video. In this paper, we propose a Time-Perception Enhanced Video Grounding via Boundary Perception and Temporal Reasoning aimed at mitigating LLMs’ difficulties in understanding the discrepancies between video and text temporality. Specifically, to address the inherent biases in current datasets, we design a series of boundary-perception tasks to enable LLMs to capture accurate video temporality. To tackle LLMs’ insufficient understanding of temporal information, we develop specialized tasks for boundary perception and temporal relationship reasoning to deepen LLMs’ perception of video temporality. Our experimental results show significant improvements across three datasets: ActivityNet, Charades, and DiDeMo (achieving up to 11.2% improvement on R@0.3), demonstrating the effectiveness of our proposed temporal awareness-enhanced data construction method.
Anthology ID:
2025.coling-main.655
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9804–9813
Language:
URL:
https://aclanthology.org/2025.coling-main.655/
DOI:
Bibkey:
Cite (ACL):
Xuefen Li, Bo Wang, Ge Shi, Chong Feng, and Jiahao Teng. 2025. Mitigating the Discrepancy Between Video and Text Temporal Sequences: A Time-Perception Enhanced Video Grounding method for LLM. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9804–9813, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Mitigating the Discrepancy Between Video and Text Temporal Sequences: A Time-Perception Enhanced Video Grounding method for LLM (Li et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.655.pdf