EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ETR: Event-Centric Temporal Reasoning for Question-Conditioned Video Question Answering

Lingmin Pan, Ziyi Gao, Yueming Zhu, Fuchen Chen, Chengyuan Zhang, Dan Yin, Yong Cai, Siqiao Tan, Lei Zhu

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.

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →