Motion Focus Recognition in Fast-Moving Egocentric Video

2026-01-12

arXiv.org

AI Summary

This work addresses the limited understanding of athletic intent in existing egocentric video datasets, which predominantly focus on action recognition and lack support for high-speed sports scenarios. To bridge this gap, we introduce motion intent recognition into egocentric fast-motion video analysis for the first time. We propose a foundation model–based approach for real-time focus-of-motion identification that infers the wearer’s intent through camera pose estimation. By integrating a sliding-batch inference mechanism with system-level optimizations, our method achieves real-time performance with low memory consumption on a newly curated dataset. The resulting framework is deployable on edge devices, offering an efficient and practical solution for intent-aware analysis in motion-intensive environments.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Motion and Path Planning
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

From Vision-Language-Action (VLA) systems to robotics, existing egocentric datasets primarily focus on action recognition tasks, while largely overlooking the inherent role of motion analysis in sports and other fast-movement scenarios. To bridge this gap, we propose a real-time motion focus recognition method that estimates the subject's locomotion intention from any egocentric video. We leverage the foundation model for camera pose estimation and introduce system-level optimizations to enable efficient and scalable inference. Evaluated on a collected egocentric action dataset, our method achieves real-time performance with manageable memory consumption through a sliding batch inference strategy. This work makes motion-centric analysis practical for edge deployment and offers a complementary perspective to existing egocentric studies on sports and fast-movement activities.

Problem

• motion focus recognition
• egocentric video
• fast-moving scenarios
• locomotion intention
• sports analysis

Innovation

• motion focus recognition
• egocentric video
• real-time inference
• camera pose estimation
• edge deployment