Metraipolis › archive › dc_6b5a44efea86
DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding — arXiv:2609.08850
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08850
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:12:26.395Z
- SHA-256 of the archived text
d2ee20d26e9a5fc090ccd29396631076e392b5cf809376c8f82aeed11b06df26- Stable URL of this page
https://metraipolis.com/documento/dc_6b5a44efea86
How to cite
DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding — arXiv:2609.08850 — arXiv (en), https://arxiv.org/abs/2609.08850 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b5a44efea86 (Metraipolis archive dc_6b5a44efea86, sha256 d2ee20d26e9a5fc090ccd29396631076e392b5cf809376c8f82aeed11b06df26)
BibTeX
@misc{dc6b5a44efea86,
title = {DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding — arXiv:2609.08850},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08850},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b5a44efea86; sha256 d2ee20d26e9a5fc090ccd29396631076e392b5cf809376c8f82aeed11b06df26},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08850. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries, yet collecting dense temporal annotations and training task-specific models remain costly and brittle under distribution shift. Recent training-free VTG approaches mitigate this issue by directly matching pretrained vision-language representations, but they still face two fundamental information bottlenecks: frame-wise visual encoding overlooks temporal dynamics, while fixed query embeddings cannot resolve query ambiguity. To address these issues, we propose DSE-VTG, a \underline{D}ual-\underline{S}ide \underline{E}nhancement framework that addresses both without any task-specific training. On the visual side, Multi-scale Similarity Fusion (MSF) combines frame- and clip-level similarities into a unified, temporally aware similarity profile. On the textual side, Query-level Test-Time Adaptation (Q-TTA) optimizes a lightweight additive offset to adapt the query embedding to the video at test time, without finetuning the backbone or calling external large language models. Extensive experiments on three standard and two OOD benchmarks show that DSE-VTG achieves state-of-the-art performance among training-free methods. On Charades-STA, it improves mIoU over the strongest prior training-free method by 5.61 points. Under distribution shift, DSE-VTG reaches 50.86 mIoU on Charades-CG Novel-Word, surpassing the strongest supervised baseline by 2.76 mIoU. Our code will be released upon acceptance.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.08850 — 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 2026-10-16T14:49:57.357Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).