Metraipolis › archive › dc_bb2baa2b094f

Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding — arXiv:2609.24127

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24127
License (as archived)
CC0-1.0
Archived
2026-10-09T22:05:09.728Z
SHA-256 of the archived text
b954c48054803b7646741803a893c1ba1d2daab1f2e7e3c023893835dec133dc
Stable URL of this page
https://metraipolis.com/documento/dc_bb2baa2b094f

How to cite

Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding — arXiv:2609.24127 — arXiv (en), https://arxiv.org/abs/2609.24127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb2baa2b094f (Metraipolis archive dc_bb2baa2b094f, sha256 b954c48054803b7646741803a893c1ba1d2daab1f2e7e3c023893835dec133dc)
BibTeX
@misc{dcbb2baa2b094f,
  title = {Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding — arXiv:2609.24127},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24127},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb2baa2b094f; sha256 b954c48054803b7646741803a893c1ba1d2daab1f2e7e3c023893835dec133dc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.24127 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T21:45:20.991Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).