Metraipolis › archive › dc_05ea3d88eb8f

SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection — arXiv:2609.13966

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13966
License (as archived)
CC0-1.0
Archived
2026-10-15T22:50:49.521Z
SHA-256 of the archived text
ef1d1f0aac71e33f6c869866e4f1d9a8d0c93f63811af225ecc1f1c4ea01b345
Stable URL of this page
https://metraipolis.com/documento/dc_05ea3d88eb8f

How to cite

SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection — arXiv:2609.13966 — arXiv (en), https://arxiv.org/abs/2609.13966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_05ea3d88eb8f (Metraipolis archive dc_05ea3d88eb8f, sha256 ef1d1f0aac71e33f6c869866e4f1d9a8d0c93f63811af225ecc1f1c4ea01b345)
BibTeX
@misc{dc05ea3d88eb8f,
  title = {SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection — arXiv:2609.13966},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13966},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_05ea3d88eb8f; sha256 ef1d1f0aac71e33f6c869866e4f1d9a8d0c93f63811af225ecc1f1c4ea01b345},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video highlight detection aims to identify temporally important segments that capture the most informative or engaging events in a video. Reliable prediction therefore requires not only discriminative segment representations but also preservation of the temporal relationships among neighboring and distant segments. The information bottleneck principle has proven effective for learning compact and task-relevant representations, yet it has not been explored for video highlight detection, and applying conventional formulations directly would overlook inter-segment relational structure and distort highlight relevant temporal organization during compression. We therefore introduce the Sliced Gromov-Monge Gap (SGMG), a structure aware regularizer that measures the excess relational distortion induced by a prescribed source-to-bottleneck mapping relative to an optimal sliced structural correspondence. Building on SGMG, we develop SGWIB, an information-bottleneck framework for single-modal video highlight detection that learns compact bottleneck representations while preserving inter-segment temporal structure. We further introduce Home-Away-Related Contextual Pseudo-Labels and a contextual disentanglement module that reduce sports-specific contextual bias by separating highlight oriented information from contextual patterns. Experiments on MrHiSum and MoSu show that SGWIB attains the best Kendall's tau, Spearman's rho, mAP@50, and mAP@30 among the compared single-modal methods on both datasets. On MrHiSum, the visual model improves the strongest previous results by 0.031, 0.031, 0.87, and 0.75 on these four metrics, respectively. These results show that structure-aware information-bottleneck regularization combined with contextual disentanglement improves segment-level highlight prediction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.13966 — 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 2026-10-15T22:29:03.599Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).