SOURCE-LINKED INTELLIGENCE

Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on simple queries. They largely overlook the compositional queries prevalent in real-world scenarios, where a target must be disambiguated by jointly reasoning about its attributes and relations to other entities. To bridge this gap, we propose Compositional Spatio-Temporal Video Grounding (CompSTVG), a task that requires models to process complex textual queries where every intertwined attribute and relational cue is essential for disambiguation. To

Read original source ↗ Open in workspace

recordType

paper

region

Global