New Gait Recognition Method Uses Mixture of Experts to Handle Occlusions

Researchers have introduced GaitMoE, a novel approach to gait recognition that addresses challenges posed by occlusions in real-world scenarios. This method frames gait recognition as an action detection problem, utilizing a Mixture of Experts (MoE) architecture. The system comprises Mixture of Temporal Experts (MTE) and Mixture of Action Experts (MAE) to adaptively construct action anchors and proposals, enabling accurate action detection even with missing or noisy information. To facilitate research in this area, the team has also created OccGait, a new database specifically designed for occluded gait recognition scenarios. AI

IMPACT Introduces a new method for improving AI's ability to identify individuals based on their gait, even when parts of their body are obscured.

RANK_REASON Publication of a new research paper on arXiv detailing a novel method and dataset. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• GaitMoE
• Gait recognition
• Mixture of Action Experts
• Mixture of Experts
• Mixture of Temporal Experts
• OccGait

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →