CVPR Findings2026
StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios
Yifei Wang, Zhenkai Li, Tianwen Qian, Huanran Zheng, Zheng Wang, Yuqian Fu, Xiaoling Wang
Abstract
As embodied intelligence advances toward real-world deployment, the ability to continuously perceive and reason over streaming visual inputs becomes essential. In such settings, an agent must maintain situational awareness of its environment, comprehend the interactions with surrounding entities, and dynamically plan actions informed by past observations, current contexts, and anticipated future events. To facilitate progress in this direction, we introduce StreamEQA, the first benchmark designed for streaming video question answering in embodied scenarios. StreamEQA evaluates existing MLLMs along two orthogonal dimensions: Embodied and Streaming. Along the embodied dimension, we categorize the questions into three levels: perception, interaction, and planning, which progressively assess a model's ability to recognize fine-grained visual details, reason about agent-object interactions, and perform high-level goal-directed reasoning. For the streaming dimension, questions are divided into backward, real-time, and forward reasoning, with each mode relying on a distinct temporal context. Built upon 156 independent long videos, StreamEQA defines 42 tasks and generates approximately 21K question-answer pairs with precise timestamps through a hybrid pipeline combining automated generation and human refinement. Evaluations of 13 state-of-the-art video-LLMs reveal that, despite strong performance on conventional benchmarks, these models still struggle with streaming video understanding in embodied scenarios. We hope StreamEQA will catalyze research on streaming video understanding for embodied applications.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone cites Learning Transferable Visual Models From Natural Language Supervision
- VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation cites EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
Cited by top-tier papers1
Builds on23
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- NuScenes-QA: A Multi-Modal Visual Question Answering Benchmark for Autonomous Driving ScenarioTianwen Qian, Jingjing Chen, Linhai Zhuo, Yang Jiao et al.AAAI 2024 · 314 citations
- EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackboneShraman Pramanick, Yale Song, Sayan Nag, Kevin Qinghong Lin et al.ICCV 2023 · 152 citations
- MovieChat: From Dense Token to Sparse Memory for Long Video UnderstandingEnxin Song, Wenhao Chai, Guanhong Wang, Yucheng Zhang et al.CVPR 2024 · 95 citations
- VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision ComputationShiwei Wu, Joya Chen, Kevin Qinghong Lin, Qimeng Wang et al.NeurIPS 2024 · 78 citations
Related papers
- Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene UnderstandingYue Fan, Xiaojian Ma, Rongpeng Su, Jun Guo et al.ICCV 2025 · 2 citations
- GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual AgentsYunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang et al.ACL 2026 · 2 citations
- Streaming Video Instruction TuningJiaer Xia, Peixian Chen, Mengdan Zhang, Xing Sun et al.CVPR 2026 · 28 citations
- StreamingEval: A Unified Evaluation Framework towards Realistic Streaming Video UnderstandingGuowei Tang, Tianwen Qian, Huanran Zheng, Yifei Wang et al.ACL Findings 2026
- Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint FramesSahithya Ravi, Gabriel Herbert Sarch, Vibhav Vineet, Andrew D. Wilson et al.EMNLP 2025 · 1 citation
