Metraipolis › archive › dc_236cf3a26cbe

Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features — arXiv:2609.25837

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25837
License (as archived)
CC0-1.0
Archived
2026-10-08T16:39:22.134Z
SHA-256 of the archived text
09b61d8a59d3e03ba7f0243289caa69770486d935575e77eed101dab2ad8503b
Stable URL of this page
https://metraipolis.com/documento/dc_236cf3a26cbe

How to cite

Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features — arXiv:2609.25837 — arXiv (en), https://arxiv.org/abs/2609.25837 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_236cf3a26cbe (Metraipolis archive dc_236cf3a26cbe, sha256 09b61d8a59d3e03ba7f0243289caa69770486d935575e77eed101dab2ad8503b)
BibTeX
@misc{dc236cf3a26cbe,
  title = {Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features — arXiv:2609.25837},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25837},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_236cf3a26cbe; sha256 09b61d8a59d3e03ba7f0243289caa69770486d935575e77eed101dab2ad8503b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25837. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This work presents a video summarization algorithm based on multi-object tracking and person reidentification. We integrate facial embeddings, 3D body-shape features, and visual appearance into a unified tracking framework. These representations enable hierarchical identity assignment and tracking through bidirectional anchoring, which robustly recovers trajectories under severe occlusion or low visual quality. From these stable trajectories, we generate a compact set of summaries for each identity. We select keyframes using a multi-factor weighting scheme that optimizes biometric clarity, social interaction, and motion dynamics, while Adaptive Non-Maximum Suppression ensures temporal diversity. Evaluation on a custom dataset demonstrates tracking stability, achieving an IDF1 of 97.89% and a MOTA of 95.79%. Compared to Top-K selection, our algorithm also increases visual diversity by 146%, temporal coverage by 89%, and information retrievability by 3.5%.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.25837 — 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 2026-10-08T15:56:18.149Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).