SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding

NeurIPSOral2025

Authors
Yuan Zang, Zitian Tang, Junho Cho, Jaewook Yoo, Chen Sun
Affiliation
Brown University
Venue
NeurIPS 2025
Track
Oral

TL;DR

We propose a unified and generalizable framework for object state recognition in video data.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

graph video

← All NeurIPS 2025 Oral papers · Browse the whole archive