Search

Home
People
Join Us
News
Projects
Publications
Datasets
Teaching
Sponsors
Contact

How Much 3D Do Video Foundation Models Encode?

Zixuan Huang, Xiang Li, Zhaoyang Lv, James Matthew Rehg

June 2026

Type

Conference paper

Related

Decoding Children's Gait Behavior
Kirin: Animal Motion Generation from In-the-Wild Video
Layer-Aware Video Composition via Split-then-Merge
Narrative-Driven Paper-to-Slide Generation via ArcDeck
STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding

Powered by the Academic theme for Hugo.

Cite