Research map / Vision-language and multimodal / Robot action and navigation
SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
Yuan Zang, Zitian Tang, Junho Cho, Jaewook Yoo, Chen Sun
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes SAGE, a unified framework that uses state-action graph embedding to recognize object states in videos and generalize to unseen actions and objects.
Problem
Recognizing physical object states and their transformations in videos; pretrained vision-language models struggle with nuanced dynamics and temporal context, and specialized object state recognition frameworks fail to generalize to unseen actions or objects.
Approach
A unified framework that represents object states and actions in a state-action graph and learns embeddings over it, aiming for generalization to unseen action and object combinations (details beyond the abstract not available).
Closest papers by meaning
- Learning Object State Changes in Videos: An Open-World Perspective (CVPR 2024 · similarity 0.89)
- Joint Discovery of Object States and Manipulation Actions (ICCV 2017 · similarity 0.89)
- MOSCATO: Predicting Multiple Object State Change Through Actions (ICCV 2025 · similarity 0.88)
- SD2Actor: Continuous State Decomposition via Diffusion Embeddings for Robotic Manipulation (ICCV 2025 · similarity 0.88)
- DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control (NeurIPS 2026 · similarity 0.87)
- Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
