Video Question Answering

Also known as VQA

Video question answering asks models to identify events, people, actions, and relationships in video, including when things happen and why. Approaches include vision-language models, question-aware frame selection and retrieval, temporal memory, scene graphs, and agentic systems that inspect evidence with tools. Benchmarks test settings such as long-form and streaming video, egocentric activity, causal reasoning, and precise temporal grounding. A central challenge is that high answer accuracy can coexist with weak use of visual evidence, poor temporal grounding, and overconfidence when evidence is incomplete.

Latest papers

185 papers25 papers in the last four weeks, up 47% on the four weeks before. 0.1% of all new papers.

CrossView: Can Vision-Language Models Reason Across Cameras?
Aug 16, 2026Sahil Shah, S P Sharan, Harsh Goel +4VLM Evaluation Video Question Answering
The University of Texas at Austin, Austin TX, USA · Independent Researcher, USA
StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs
Aug 13, 2026Joya Chen, Zeyun Zhong, Mike Zheng ShouMemory-Augmented VLMs Streaming Video Understanding
National University of Singapore · Karlsruhe Institute of Technology
VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding
Aug 12, 2026Fan Zhang, Guangming Yao, Jinyang Wu +6AI Agent Benchmarks Video Question Answering
The Chinese University of Hong Kong · Ant Group · Tsinghua University +2
R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video
Aug 11, 2026Ke Ma, Yamin Mao, Weiming Li +5Egocentric VQA Video Question Answering
College of Design and Innovation Tongji University Shanghai, China · Samsung R&D Institute China - Beijing Beijing, China · Shanghai Jiao Tong University Shanghai, China +2
FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding
Aug 11, 2026Fufangchen Zhao, Jinhu Fu, Jiachen Lei +3Counterfactual Evaluation Video Question Answering
State Key Laboratory of Networking and Switching Technology, BUPT · AMAP, Alibaba Group
VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation
Aug 10, 2026Jiajun Xu, Yanghao Zhou, Jingyun Liao +6Web Application Generation Video-Language Model Evaluation
University of Technology Sydney · Beijing Institute of Technology · Hunan University +4
REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering
Aug 9, 2026Caijun Yan, Yang Zhou, Meixing Shi +4Video Question Answering Long-Video QA
1Zhejiang University · 2Shanghai AI Laboratory
SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning
Aug 8, 2026Yizhi Li, Jiawei Jiang, Guanhong Wang +2Sports Video Analysis Video Question Answering
Zhejiang University Hangzhou, China · Beijing Jiaotong University Beijing, China
I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning
Aug 7, 2026Shibo Gao, Chongxiao Wang, Chenglong Huang +10Video Question Answering Vision-Language Grounding
School of Computing and Communications Lancaster University Lancaster, United Kingdom
DAEP: Difficulty-Aware Evidence Planning for Medical Video Corpus Temporal Answer Grounding
Aug 7, 2026Tianjian He, Yujie Liu, Zhiping Huang +1Temporal Video Grounding Video Understanding
TikTok, ByteDance, China · Beijing Institute of Graphic Communication, Beijing, China · Lingnan University, Hong Kong, China
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
Aug 6, 2026Qifeng Zhang, Kaixiang Huang, Heng Dong +6VLM Evaluation Spatial Reasoning Benchmarks
ByteDance Seed · Zhejiang University · National University of Singapore +1
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
Aug 5, 2026Yuqian Fu, Tianwen Qian, Yanjun Li +30Egocentric VQA Video Question Answering
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
Aug 5, 2026Benlei Cui, Ruize Wang, Junjie Li +9Video Question Answering Long-Video Understanding
Yuvion Team, Alibaba Group · Zhejiang University · Beihang University +1
Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering
Aug 4, 2026Haotian Xia, Zilin Xiao, Junbo Zou +2Video Question Answering Latent Visual Reasoning
Department of Computer Science, Rice University · College of Sciences, Georgia Institute of Technology
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
Aug 4, 2026Zhen Fang, Yu Zeng, Wenxuan Huang +17Deep Research Agents Video Question Answering
GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience
Aug 3, 2026Sitong Gong, Caixin Kang, Tianyu Yan +7Streaming Video Understanding Video Question Answering
1Dalian University of Technology · 2Alaya Lab · 3The University of Tokyo +1
PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs
Aug 3, 2026Zhongjie Ba, Shengwang Xu, Peng Cheng +4Video-Language Model Evaluation Video Question Answering
State Key Lab. of Blockchain and Data Security, Zhejiang University, Hangzhou, China · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou, Zhejiang, China · Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
Continual Video-MLLM Adaptation over Evolving Domains
Jul 21, 2026Rui Cheng, Meixing Shi, Yuxiang Cai +3Video Question Answering Domain-Incremental Learning
School of Software Technology, Zhejiang University, Ningbo, China · Zhejiang Key Laboratory of Digital-Intelligence Service Technology, China · Hong Kong Polytechnic University, Hong Kong SAR +1
EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent
Jul 15, 2026Junlong Li, Junxi Li, Yuxiang Yang +3Egocentric VQA Video Question Answering
The Hong Kong Polytechnic University Hong Kong, China
What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation
Jul 14, 2026Farrukh RahmanVLM Evaluation Temporal Reasoning
Microsoft · Georgia Institute of Technology
Evidence-Backed Video Question Answering
Jul 13, 2026Shijie Wang, Honglu Zhou, Ziyang Wang +5Temporal Video Grounding Video Question Answering
Salesforce, Palo Alto, CA, USA · Brown University, Providence, RI, USA
Do Video-LLMs Actually Watch? Diagnosing Character-Tracking Failures in Long-Form Video
Jul 13, 2026Mohammad Al-Ratrout, Shayla Sharmin, Aditya Raikwar +1Visual Object Tracking Video-Language Model Evaluation
TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understanding
Jul 13, 2026Thanh-Nhan Vo, Thanh-Khoi Nguyen, Trong-Thuan Nguyen +2Tool Use in VLMs Sports Video Analysis
University of Science, VNU-HCM, Ho Chi Minh City, Vietnam · 2Vietnam National University, Ho Chi Minh City, Vietnam
EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage
Jul 7, 2026Max Gonzalez Saez-Diez, Jihoon Chung, Adam D. Wolsky +5Video Question Answering Egocentric Video Understanding
Princeton University · University of Pennsylvania
Overview of the NLPCC 2026 Shared Task 1: Difficulty-Aware Multilingual and Multimodal Medical Instructional Video Understanding Evaluation
Jul 7, 2026Shenxi Liu, Kan Li, Mingyang Zhao +2Multimodal IR Temporal Video Grounding
School of Computer Science and Technology, Beijing Institute of Technology · Department of Computing, The Hong Kong Polytechnic University · Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning
Jul 3, 2026Zhenkun Gao, Yicheng Bao, Jinlong Peng +13Multimodal RAG Video Question Answering
East China Normal University · Tencent Youtu Lab · HFIPS, Chinese Academy of Sciences +3
K9-Bench: Evaluating Multimodal LLMs on Canine-Centric Videos
Jul 2, 2026Khush Attarde, Yusuf Ali, Megha Thukral +3Video Understanding Multimodal Large Language Models
Ogmen Robotics Inc., Massachusetts, USA · Georgia Institute of Technology, Atlanta, USA
ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA
Jul 2, 2026Minkuk Kim, Suyong Yun, Young Tae Kim +3Efficient VLM Inference Video Question Answering
Kyung Hee University, Republic of Korea · Electronics and Telecommunications Research Institute (ETRI), Republic of Korea
Accuracy and Cost Claims Do Not Survive Re-Execution in Agentic VideoQA
Jul 1, 2026Rama AlHamidi, Aseel Mohamed, Rasul Khanbayov +3AI Agent Evaluation Video Question Answering
Electrical and Computer Engineering, Texas A&M University, TX, United States · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar
From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA
Jun 29, 2026Sena Korkut, María Alejandra Bravo Sarmiento, Sanghwan Kim +1VLM Evaluation Vision-Language Models
Technical University of Munich, Munich, Germany · Helmholtz Zentrum München, Munich, Germany · Munich Center for Machine Learning, Munich, Germany

Aug 16, 2026J/K move · Enter open · S save

CrossView: Can Vision-Language Models Reason Across Cameras?

Sahil Shah, S P Sharan, Harsh Goel, Manvik Pasula+3

The University of Texas at Austin, Austin TX, USA · Independent Researcher, USA

VLM Evaluation Video Question Answering VLMs for Autonomous Driving

Open paper AskPDF arXiv

Video understanding benchmarks have long centered on single-camera settings, where modern multi-modal language models achieve strong performance across image and video tasks. Yet, the real world runs on multi-camera networks: autonomous vehicles, security systems, and robots all gather data across many simultaneous views. We argue that this is not simply "more" of the single-camera problem; it is fundamentally different. Multi-camera reasoning requires handling context that scales with the number of views, resolving occlusions visible from only a subset of cameras, judging which views matter, and integrating evidence across perspectives that may overlap or diverge. Current models struggle with exactly these challenges, yet no benchmark systematically targets them. We introduce CrossView, a multi-camera video question-answering benchmark spanning autonomous driving, security surveillance, egocentric/exocentric video, and robotics. Evaluation of proprietary models, such as GPT-5.2, and open-source models, like Qwen3-VL, reveals consistently low accuracy, with open-source models trailing by a wide margin. Performance scales strongly with a model's ability to jointly process multiple viewpoints, positioning CrossView as a rigorous benchmark for multi-camera video. We open-source our code and dataset at https://utaustin-swarmlab.github.io/CrossView.