ETR: Event-Centric Temporal Reasoning for Question-Conditioned Video Question Answering
Mathematics · 07.03.2026 · 14 (5) · 913
DOI: 10.3390/math14050913 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 07.03.2026. Verfasst von Lingmin Pan und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Yuelu Mountain Laboratory Seed Industry Special Project, Natural Science Foundation of Hunan Province.
Abstract (Originalsprache)
Video Question Answering (VideoQA) requires a deep understanding of dynamic video content, integrating spatial reasoning, temporal dependencies, and language comprehension. Existing methods often struggle with long or semantically complex videos due to the lack of question-guided keyframe weight adjustment and the absence of question-aligned cross-modal description generation. To address these challenges, we propose ETR (Event-centric Temporal Reasoning), an adaptive framework for VideoQA. ETR introduces three key mechanisms: (i) a hierarchical weight adjustment selector to identify questions requiring event-centric temporal reasoning; (ii) a T-Route that segments videos into semantically coherent events and dynamically adjusts keyframe weights with question intent; and (iii) a question-conditioned prompting strategy that focuses on key objects to generate textual prompts aligned with a question’s semantics. This hierarchical and adaptive design effectively balances visual and textual information, enhances temporal reasoning, and improves object-centric alignment. Experiments on two datasets demonstrate that ETR achieves competitive performance in fine question-aware VideoQA.
Förderung
- National Natural Science Foundation of China
- Yuelu Mountain Laboratory Seed Industry Special Project
- Natural Science Foundation of Hunan Province
Zitieren
APA
Pan, L., Gao, Z., Zhu, Y., Chen, F., Zhang, C., Yin, D., Cai, Y., Tan, S., & Zhu, L. (2026). ETR: Event-Centric Temporal Reasoning for Question-Conditioned Video Question Answering. Mathematics, 14(5), 913. https://doi.org/10.3390/math14050913
Vancouver
Pan L, Gao Z, Zhu Y, Chen F, Zhang C, Yin D, et al. ETR: Event-Centric Temporal Reasoning for Question-Conditioned Video Question Answering. Mathematics. 2026;14(5):913. doi:10.3390/math14050913
BibTeX
@article{Pan2026,
author = {Pan, Lingmin and Gao, Ziyi and Zhu, Yueming and Chen, Fuchen and Zhang, Chengyuan and Yin, Dan and Cai, Yong and Tan, Siqiao and Zhu, Lei},
title = {ETR: Event-Centric Temporal Reasoning for Question-Conditioned Video Question Answering},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {5},
pages = {913},
doi = {10.3390/math14050913}
}
EUVIMED