EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
Sheng Zhou, Junbin Xiao, Qingyun Li, Yicong Li, Xun Yang, Dan Guo, Meng Wang, Tat-Seng Chua, Angela Yao
Abstract
Book-related Gameplay Q: What number is on the man's jersey? A: 14. Q: What is written on the road before the zebra crossing? A: Stop. Egocentric Scene-Text VideoQA EgoTextVQA-Outdoor EgoTextVQA-Indoor Q: What is the state of microwave before the person gets something from it? A: Closed. Egocentric VideoQA (EgoTaskQA) Q: What should I do to clean the pot after cooking? A: Use the fairy dishwashing liquid and scrub the pot with a cloth. 150.1s 80.8s 180s Q Kitchen 40.4s 60.2s EgoTextVQA-Indoor Scene-Text VideoQA (RoadTextVQA) Scene-Text VQA (TextVQA) Q: What should I be cautious of when driving through this area? A: Children crossing the road. Intention Reasoning 6.5s 4.3s 8.2s 10s Q 7.4s EgoTextVQA-Outdoor Figure 1. Our EgoTextVQA aims for QA assistance involving scene text from an ego-perspective mainly in outdoor driving (EgoTextVQA-Outdoor) and indoor house-keeping (EgoTextVQA-Indoor), with the questions reflecting the real user needs yet without the visual focus on scene text. Benchmarking results show that all models struggle on EgoTextVQA, highlighting continued efforts for improvements.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 88996305-d6ed-4f1d-9cda-816f68a400a3Cited by top-tier papers23
- EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question AnsweringYanjun Li, Yuqian Fu, Tianwen Qian, Qi'ao Xu et al.AAAI 2026 · 14 citations
- EgoSound: Benchmarking Sound Understanding in Egocentric VideosBingwen Zhu, Yuqian Fu, Qiaole Dong, Guolei Sun et al.CVPR 2026 · 7 citations
- Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion ReasoningZhiyuan Han, Beier Zhu, Yanlong Xu, Peipei Song et al.ACM MM 2025 · 7 citations
- Ego-Grounding for Personalized Question-Answering in Egocentric VideosJunbin Xiao, Shenglang Zhang, Pengxiang Zhu, Angela YaoCVPR 2026 · 7 citations
- Interaction-aware Representation Modeling With Co-Occurrence Consistency for Egocentric Hand-Object ParsingYUEJIAO SU, Yi Wang, Lei Yao, Yawen Cui et al.ICLR 2026 · 5 citations
Builds on17
- CogVLM: Visual Expert for Pretrained Language ModelsWeihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong et al.NeurIPS 2024 · 858 citations
- Ego4D: Around the World in 3, 000 Hours of Egocentric VideoKristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis et al.CVPR 2022 · 525 citations
- Egocentric Video-Language PretrainingKevin Qinghong Lin, Jinpeng Wang, Mattia Soldan, Michael Wray et al.NeurIPS 2022 · 306 citations
- Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language ModelsMuhammad Maaz, Hanoona Abdul Rasheed, Salman Khan, Fahad KhanACL 2024 · 279 citations
- Deconfounded Video Moment Retrieval with Causal InterventionXun Yang, Fuli Feng, Wei Ji, Meng Wang et al.SIGIR 2021 · 198 citations
Related papers
- Look Before You Speak: Visually Contextualized UtterancesPaul Hongsuck Seo, Arsha Nagrani, Cordelia SchmidCVPR 2021
- EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language ModelsSijie Cheng, Zhicheng Guo, Jingwen Wu, Kechen Fang et al.CVPR 2024
- EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging BenchmarkDeheng Zhang, Yuqian Fu, Runyi Yang, Yang Miao et al.ICLR 2026 · 19 citations
- Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric VideosChiara Plizzari, Alessio Tonioni, Yongqin Xian, Achin Kulshrestha et al.CVPR 2025
- Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMsInsu Lee, Wooje Park, Jaeyun Jang, Minyoung Noh et al.NeurIPS 2025 · 8 citations
