Metraipolis › archive › dc_0c326b22bc29
Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding — arXiv:2608.28192
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28192
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:33:11.647Z
- SHA-256 of the archived text
834dcf55fda6c08c72a07dad6a5a65ab79adc6b184abfda667b8158df3048462- Stable URL of this page
https://metraipolis.com/documento/dc_0c326b22bc29
How to cite
Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding — arXiv:2608.28192 — arXiv (en), https://arxiv.org/abs/2608.28192 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c326b22bc29 (Metraipolis archive dc_0c326b22bc29, sha256 834dcf55fda6c08c72a07dad6a5a65ab79adc6b184abfda667b8158df3048462)
BibTeX
@misc{dc0c326b22bc29,
title = {Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding — arXiv:2608.28192},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28192},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c326b22bc29; sha256 834dcf55fda6c08c72a07dad6a5a65ab79adc6b184abfda667b8158df3048462},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28192. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval. Existing multimodal large language models typically serialize dense localization trajectories autoregressively, causing decoding latency to grow with tube length and allowing localization errors to propagate across time. We introduce Parallel Tube Decoding (PTD), a generative formulation that decomposes grounding into a temporal block followed by time-conditioned spatial blocks decoded simultaneously. This removes both token-level and trajectory-level dependencies, reducing the sequential decoding depth to a fixed $1 + 1$ rounds, independent of tube length. To enable parallel spatial generation, we introduce Decoupled Block Attention, which preserves access to shared video-query context while eliminating cross-box dependencies, together with localization-aware policy optimization for temporal boundaries and spatial geometry. On VidSTG, PTD reduces Tube Completion Latency by 79x and increases spatial decoding throughput by 92x over standard autoregressive decoding, while also improving grounding accuracy. With a compact 4B backbone, our model performs favorably well on VidSTG and HC-STVG, and generalizes zero-shot to temporal grounding, grounded VideoQA, and referring video object tracking. Our results show parallel tube generation is an efficient and effective alternative to autoregressive localization in videos. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28192 — 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 2026-10-17T11:10:05.311Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).