Metraipolis › archive › dc_bb00fab55724
Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval — arXiv:2609.04800
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04800
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T23:41:11.202Z
- SHA-256 of the archived text
93e5fe4c333ed826506e6a24d6d33e6690258d76e5854532124fbe9a4ecc0687- Stable URL of this page
https://metraipolis.com/documento/dc_bb00fab55724
How to cite
Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval — arXiv:2609.04800 — arXiv (en), https://arxiv.org/abs/2609.04800 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb00fab55724 (Metraipolis archive dc_bb00fab55724, sha256 93e5fe4c333ed826506e6a24d6d33e6690258d76e5854532124fbe9a4ecc0687)
BibTeX
@misc{dcbb00fab55724,
title = {Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval — arXiv:2609.04800},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04800},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb00fab55724; sha256 93e5fe4c333ed826506e6a24d6d33e6690258d76e5854532124fbe9a4ecc0687},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04800. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos that contain moments relevant to a text query. Since the target moment occupies only a portion of the video, PRVR requires retrieval based on fine-grained understanding beyond coarse video-level matching. However, existing methods often rely on frozen CLIP frame features, which lack temporal understanding. Even with recent progress in parameter-efficient CLIP adaptation, video-level predictions can still be supported by imprecise frame-level evidence. In this paper, we propose an Intrinsic Temporal Adaptation (ITA) framework for PRVR. First, our Backbone-Internal Temporal Adaptation allows the last few visual transformer layers to attend over groups of neighboring frames. This provides temporally aware frame embeddings while keeping CLIP frozen and training only adaptation parameters. Second, we introduce Affinity-Weighted Gradient Propagation to address the weakly supervised nature of PRVR, softly aggregating top-$k$ frames based on text-frame affinities and propagating learning signals to multiple query-relevant frames. Our method achieves state-of-the-art performance on PRVR benchmarks, demonstrates robust cross-dataset transfer, and retrieves substantially more accurate frame-level evidence within ground-truth query-relevant moments. Our code is available at this http URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.04800 — 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 2026-10-16T23:16:11.411Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).