SOURCE-LINKED INTELLIGENCE

Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Atomic activity understanding aims to recognize and localize structured traffic behaviors that jointly encode motion patterns and their grounding in road topology. Unlike conventional action recognition, atomic activities are multi-agent, multi-label, and topology-aware: multiple activities co-occur while many agents remain inactive. We introduce Action-Slot, a structured action-centric representation learning framework. Slot attention is widely used for object-centric decomposition, but its permutation-invariant design and object-level inductive bias are misaligned with atomic activity semant

Read original source ↗ Open in workspace

recordType

paper

region

Global