HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 23 Jul 2025 09:12:37 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6880a785-702" expires: Tue, 30 Dec 2025 04:31:47 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 6D17:3ABDEF:985EF0:AB5005:69535359 accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 04:21:47 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210046-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767068507.321344,VS0,VE204 vary: Accept-Encoding x-fastly-request-id: 31657ba9d1a3beed21a299085784699723a33457 content-length: 918

Kai Jia

Welcome! I'm a researcher working on human-object interaction, 3D vision, and physical reasoning.

Publications

• Kai Jia*, Hongwen Zhang, Liang An, Yebin Liu.
  "Delving Deep into Pixel Alignment Feature for Accurate Multi-view Human Mesh Recovery"
  AAAI 2023
  [Project Page]
• Kai Jia*, Tengyu Liu*, Yixin Zhu, Mingtao Pei, Siyuan Huang.
  "PrimHOI: Compositional Human-Object Interaction via Reusable Primitives"
  ICCV 2025
  [Project Page]

Contact: kajia@umich.edu