Problem
Research questions and friction points this paper is trying to address.
Atomic Activity Understanding
Multi-Agent
Topology-Aware
Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding
🤖 AI Summary
本文通过引入Action-Slot框架解决多智能体原子活动理解问题，利用结构化动作分解和注意力差异伪掩码选择方法提高识别与定位性能。
📝 Abstract
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 semantics. We reformulate slot learning as structured activity decomposition through three designs: (1) category-aligned action slots that anchor slots to predefined activity categories, (2) parallel spatio-temporal slot updating for holistic video-level reasoning, and (3) background and negative-slot regularization that enforces competition between foreground activities and irrelevant regions. Together these establish an activity-centric inductive bias that disentangles concurrent and asynchronous activities directly from raw video. Beyond recognition, the learned representations encode transferable spatio-temporal grounding signals. We further propose an attention-difference-based pseudo mask selection framework that suppresses false positives by measuring attention changes before and after candidate region removal, enabling weakly supervised localization without dense annotations. To support systematic evaluation, we introduce TACO, a balanced synthetic dataset with full atomic activity coverage and pixel-level annotations. Experiments on OATS, TACO, and annotated nuScenes show superior recognition, strong sim-to-real transfer, and state-of-the-art weakly supervised localization.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Action-Slot
structured action-centric representation learning
category-aligned action slots
parallel spatio-temporal slot updating
background and negative-slot regularization
🔎 Similar Papers
No similar papers found.
