QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24160-24168
DOI: 10.1609/aaai.v40i29.39595 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yongdong Luo und 9 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods employ post-hoc low-response token pruning in decoder layers, they overlook the input-level semantic correlation between visual tokens and instructions (query). In this paper, we propose QuoTA, an ante-hoc training-free modular that extends existing large video-language models (LVLMs) for visual token assignment based on query-oriented frame-level importance assessment. The query-oriented token selection is crucial as it aligns visual processing with task-specific requirements, optimizing token budget utilization while preserving semantically relevant content. Specifically, (i) QuoTA strategically allocates frame-level importance scores based on query relevance, enabling one-time visual token assignment before cross-modal interactions in decoder layers, (ii) we decouple the query through Chain-of-Thoughts reasoning to facilitate more precise LVLM-based frame importance scoring, and (iii) QuoTA offers a plug-and-play functionality that extends to existing LVLMs. Extensive experimental results demonstrate that implementing QuoTA with LLaVA-Video-7B yields an average performance improvement of 3.2% across six benchmarks (including Video-MME and MLVU) while operating within an identical visual token budget as the baseline.
Zitieren
APA
Luo, Y., Chen, W., Huang, W., Yin, S., Lin, H., Huang, J., Fu, C., Ji, J., Zheng, X., & Luo, J. (2026). QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24160-24168. https://doi.org/10.1609/aaai.v40i29.39595
Vancouver
Luo Y, Chen W, Huang W, Yin S, Lin H, Huang J, et al. QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24160-24168. doi:10.1609/aaai.v40i29.39595
BibTeX
@article{Luo2026,
author = {Luo, Yongdong and Chen, Wang and Huang, Weizhong and Yin, Shukang and Lin, Haojia and Huang, Jinfa and Fu, Chaoyou and Ji, Jiayi and Zheng, Xiawu and Luo, Jiebo},
title = {QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {29},
pages = {24160--24168},
doi = {10.1609/aaai.v40i29.39595}
}
EUVIMED