Streaming VQA

VQA: Video Question Answering

Follow this topic Ask about this topic

Latest papers

8 papers5 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering
Oct 31, 2026Zhuchen Shao, Bo Chen, Klara NahrstedtStreaming VQA Video Question Answering
University of Illinois Urbana-Champaign
PACE: Plan, Attend, Check, and Emit for Training-Free Response Timing in Streaming Video Understanding
Oct 20, 2026Siqi Guo, Yuxia Chen, Wenbo Zhu +4Streaming VQA Streaming Video Understanding
Nanyang Technological University · University of Electronic Science and Technology of China · University of California, Berkeley +3
StreamAhead: Real-Time Streaming Video Question Answering via Adaptive Precomputation
Oct 18, 2026Haoyang Fan, Dhruv Parikh, Rajgopal Kannan +1Streaming VQA Video Question Answering
University of Southern California (USC), Los Angeles, CA, USA · 2DEVCOM Army Research Office
ProV-Mem: Proactive Memory for Streaming Video Question Answering
Oct 15, 2026Bingbing Wang, Jing Li, Han Gao +3Streaming VQA Video Question Answering
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China · Research Institute for Generative AI, The Hong Kong Polytechnic University, Hong Kong, China · Tencent Inc., China +1
SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding
Oct 10, 2026Senbin Xu, Zijun Zhang, Xinhua Wu +7Streaming VQA Streaming Video Understanding
Xiamen University · Beijing Institute of Technology · Fudan University +3
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
Sep 2, 2026Jitai Hao, Ke Yang, Di Yan +3Streaming VQA Streaming Video Understanding
Harbin Institute of Technology (Shenzhen)
StreamScout: Learning When to Look Deeper for Streaming Video Understanding
Aug 31, 2026Ce Zhang, Jing Bi, Jinxi He +9Efficient VLM Inference Streaming Video Understanding
Carnegie Mellon University · TikTok · University of Rochester +2
AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Apr 5, 2026Xudong Lu, Yang Bo, Jinpeng Chen +9Streaming VQA Video-Language Models
CUHK MMLab · Huawei Research

Oct 31, 2026J/K move · Enter open · S save

StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering

Zhuchen Shao, Bo Chen, Klara Nahrstedt

University of Illinois Urbana-Champaign

Streaming VQA Video Question Answering Evidence-Grounded VQA Memory-Augmented Video Understanding

Open paper AskPDF arXiv

Streaming video question answering (QA) requires real-time reasoning over continuous video streams under strict latency and active-context budgets. Current streaming vision-language models (VLMs) often give confident yet ungrounded answers when queries are ambiguous or have false premises, or when relevant visual evidence is no longer in the active context. Proactive clarification can help, but must satisfy the same latency and memory constraints. We present StreamClarify, a training-free framework for grounded streaming QA that combines a pre-answer uncertainty check with hierarchical memory. The check uses the entropy of a binary pre-answer judgment as a lightweight uncertainty score to decide whether to answer directly or request clarification. To support re-answering, a temporal-pyramid KV cache maintains a bounded active visual context, while a CPU-side semantic retrieval archive provides access to historical frames. We further construct StreamClarify-QA, a diagnostic benchmark of 1,837 QA pairs from StreamBench and OVO-Bench, spanning standard, referential ambiguity, and unanswerable scenarios. Across three VLM backbones, StreamClarify improves Macro accuracy by up to 8.2 points over backbone-matched baselines. At comparable trigger rates, entropy-based selection achieves more than 18 points higher precision than random selection in identifying initially incorrect answers. Under oracle user guidance, clarification improves Macro accuracy by up to 3.5 points. We also report a controlled, oracle-assisted Qwen3-VL simulation on Ambiguous QA with generated questions and referent-only user replies, where the entropy-gated condition improves accuracy by 8.3 points.