Metraipolis › archive › dc_0fdfe1ba007c

STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection — arXiv:2608.19987

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19987
License (as archived)
CC0-1.0
Archived
2026-10-18T12:04:43.772Z
SHA-256 of the archived text
4454776700b62e6a122248ea0442fbfdaaa76274a06f88122ddae336f7086f0e
Stable URL of this page
https://metraipolis.com/documento/dc_0fdfe1ba007c

How to cite

STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection — arXiv:2608.19987 — arXiv (en), https://arxiv.org/abs/2608.19987 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0fdfe1ba007c (Metraipolis archive dc_0fdfe1ba007c, sha256 4454776700b62e6a122248ea0442fbfdaaa76274a06f88122ddae336f7086f0e)
BibTeX
@misc{dc0fdfe1ba007c,
  title = {STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection — arXiv:2608.19987},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19987},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0fdfe1ba007c; sha256 4454776700b62e6a122248ea0442fbfdaaa76274a06f88122ddae336f7086f0e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19987. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Skeleton-based Video Anomaly Detection (VAD) offers a robust, privacy-preserving solution for identifying abnormal behaviors. To model the distribution of normal static and moving poses, recent methods train Energy-Based Models (EBMs) via Denoising Score Matching (DSM). However, directly injecting noise, required for training, into raw joint coordinates creates physically impossible poses, and this structural collapse severely worsens as the temporal window expands. To address this, we introduce STEP, a simple framework that utilizes Principal Component Analysis (PCA) to project pose sequences into a compact, whitened PC-space. Learning the data density within this well-behaved PC-space ensures that the injected noise translates into physically plausible variations, which allows the model to process longer video sequences without the performance collapse of raw coordinate baselines. Additionally, to mitigate inherent pose estimation inaccuracies arising from occlusions or motion blur, we integrate a sequence-level weighting mechanism based on the estimator's confidence scores. Operating at real-time computational efficiency, our simple and lightweight framework outperforms the previous skeleton-based state-of-the-art by 12.2% (90.1% AUROC) on the challenging UBnormal dataset and achieves highly competitive results by improving on the ShanghaiTech benchmark.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.19987 — 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 2026-10-18T12:01:57.729Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).