Hugging Face Trending Papers

Person Identification from Contextual Motion

Read the original on Hugging Face Trending Papers →

We consider the problem of identifying people based on their motion styles. We present a generative model describing the action instance creation process and derive a probabilistic identity inference scheme for two common person identification scenarios motivated by the surveillance and authentication applications.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Aug 10

I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning

arXiv:2608. 07417v1 Announce Type: cross Abstract: Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identity matching and person-centric reasoning.

By Shibo Gao, Chongxiao Wang, Chenglong Huang, Jie Ma, Haolin Shi, Fei Ding, Jing Li, Qiang Lyu, Yangyang Liu, Yang Liu, Jun Liu, Linlin Huang, Peipei Yang