Metraipolis › archive › dc_cdaa5818fdeb

Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion Matters — arXiv:2610.03276

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.03276
License (as archived)
CC0-1.0
Archived
2026-10-06T09:08:09.993Z
SHA-256 of the archived text
f50ed86864765fc105a2b2bb7a2eac03d5304113ad89cbc157d75cd09f568dad
Stable URL of this page
https://metraipolis.com/documento/dc_cdaa5818fdeb

How to cite

Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion Matters — arXiv:2610.03276 — arXiv (en), https://arxiv.org/abs/2610.03276 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdaa5818fdeb (Metraipolis archive dc_cdaa5818fdeb, sha256 f50ed86864765fc105a2b2bb7a2eac03d5304113ad89cbc157d75cd09f568dad)
BibTeX
@misc{dccdaa5818fdeb,
  title = {Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion Matters — arXiv:2610.03276},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.03276},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdaa5818fdeb; sha256 f50ed86864765fc105a2b2bb7a2eac03d5304113ad89cbc157d75cd09f568dad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03276. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video saliency prediction is inherently harder to model than static image saliency due to the additional temporal dimension. Video saliency benchmarks rest on the premise that predicting gaze on video requires utilizing temporal activity distributed across frames. Prior work has challenged this, showing that static baselines recover a significant fraction of the explainable gaze information on LEDOV, a popular video saliency dataset, and that video saliency models fail in the same places as this static baseline. We verify that this diagnosis still stands: under a more capable gold standard than the original analysis, and an updated panel of recent architectures, the strongest temporal architecture in the panel still does not substantially improve over a fine-tuned static baseline. However, it remains unclear whether the marginal gain reflects limitations of current temporal architectures or a lack of temporal patterns in the benchmark itself. We introduce SalTempto, a video saliency benchmark with greater dynamism: 224 clips of highly dynamic content, sourced from the HACS-Segments dataset so that each clip contains an event together with its lead-up and aftermath, with gaze recordings from up to 16 subjects and a training split for adapting pretrained models. On SalTempto, the static baseline recovers only about 13\% of the headroom above the centerbias, against more than half on LEDOV. A fine-tuned temporal architecture shows a substantial gain in performance over the static baseline, indicating that it does capture meaningfully more temporal information, which LEDOV fails to measure. Yet, even this SoTA model still leaves nearly half of SalTempto's headroom unexplained, indicating room for improvement in video saliency modelling. Examination of SalTempto also lets us describe human tendencies that models miss. SalTempto link: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.03276 — 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 2026-10-06T08:21:44.228Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).