EUVIMEDEUVIMED entdecken
Crossref

EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering

Yanjun Li, Yuqian Fu, Tianwen Qian, Qi'Ao Xu, Silong Dai, Danda Pani Paudel, Luc Van Gool, Xiaoling Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6592-6600

DOI: 10.1609/aaai.v40i8.37589 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yanjun Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in Multimodal Large Language Models (MLLMs) have significantly pushed the frontier of egocentric video question answering (EgocentricQA). However, existing benchmarks and studies are mainly limited to common daily activities such as cooking and cleaning. In contrast, real-world deployment inevitably encounters domain shifts, where target domains differ substantially in both visual style and semantic content. To bridge this gap, we introduce EgoCross, a comprehensive benchmark designed to evaluate the cross-domain generalization of MLLMs in EgocentricQA. EgoCross covers four diverse and challenging domains, including surgery, industry, extreme sports, and animal perspective, representing realistic and high-impact application scenarios. It comprises approximately 1,000 QA pairs across 798 video clips, spanning four key QA tasks: prediction, recognition, localization, and counting. Each QA pair provides both OpenQA and CloseQA formats to support fine-grained evaluation. Extensive experiments show that most existing MLLMs, whether general-purpose or egocentric-specialized, struggle to generalize to domains beyond daily life, highlighting the limitations of current models. Furthermore, we conduct several pilot studies, e.g., fine-tuning and reinforcement learning, to explore potential improvements. We hope EgoCross and our accompanying analysis will serve as a foundation for advancing domain-adaptive, robust egocentric video understanding.

Zitieren

APA

Li, Y., Fu, Y., Qian, T., Xu, Q., Dai, S., Paudel, D. P., Gool, L. V., & Wang, X. (2026). EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6592-6600. https://doi.org/10.1609/aaai.v40i8.37589

Vancouver

Li Y, Fu Y, Qian T, Xu Q, Dai S, Paudel DP, et al. EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6592-6600. doi:10.1609/aaai.v40i8.37589

BibTeX
@article{Li2026,
  author = {Li, Yanjun and Fu, Yuqian and Qian, Tianwen and Xu, Qi'Ao and Dai, Silong and Paudel, Danda Pani and Gool, Luc Van and Wang, Xiaoling},
  title = {EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {8},
  pages = {6592--6600},
  doi = {10.1609/aaai.v40i8.37589}
}
Kostenlos starten →