StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
cs.CV, cs.AI, cs.CL
Submitted: 2025-12-01
Updated: 2026-11-05
Terminology
Sources
- Qwen2.5-VL Technical Report
- VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- ViSpeak: Visual Instruction Feedback in Streaming Videos
- A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions
- Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
- StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
- Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
- In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
- Qwen3 Technical Report
- SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone
- Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
- Proactive Assistant Dialogue Generation from Streaming Egocentric Videos
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs