Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark

arXiv:2609.37938 · cs.CV, cs.AI, cs.RO · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.AI, cs.RO

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/lei-qi-233/EgoGears

Terminology

• Accuracy — 34× in this paper · explained in 1 episode
• Benchmark — 27× in this paper · explained in 2 episodes
• Verification — 20× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Consistency — 5× in this paper · explained in 3 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Temporal Reasoning — 4× in this paper · explained in 2 episodes
• Actor — 3× in this paper · explained in 3 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• CVF International Conference on Computer Vision Workshop — 2× in this paper
• Embodied AI — 2× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Gemma 3 Technical Report
• Gemma 4 Technical Report
• GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
• MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
• Kimi-VL Technical Report
• MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence
• EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos
• Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
• Slow-Fast Architecture for Video Multi-Modal Large Language Models
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• PROVIA: Procedure State Tracking for Online Mistake Detection in Egocentric Videos
• LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models
• Qwen3-Omni Technical Report
• SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models