Metraipolis › archive › dc_0b3ce3371cf3
Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding — arXiv:2609.31135
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31135
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:39:42.690Z
- SHA-256 of the archived text
25080bbbb6956c93167c48dfc6e4b01e6674625652a8e7ae6f7e44ae48bebe31- Stable URL of this page
https://metraipolis.com/documento/dc_0b3ce3371cf3
How to cite
Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding — arXiv:2609.31135 — arXiv (en), https://arxiv.org/abs/2609.31135 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0b3ce3371cf3 (Metraipolis archive dc_0b3ce3371cf3, sha256 25080bbbb6956c93167c48dfc6e4b01e6674625652a8e7ae6f7e44ae48bebe31)
BibTeX
@misc{dc0b3ce3371cf3,
title = {Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding — arXiv:2609.31135},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31135},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0b3ce3371cf3; sha256 25080bbbb6956c93167c48dfc6e4b01e6674625652a8e7ae6f7e44ae48bebe31},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31135. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spatio-Temporal Video Grounding (STVG) aims to localize the spatio-temporal tube in a video corresponding to a natural language query. While recent methods achieve strong performance in fully supervised, weakly supervised, and zero-shot settings, they typically rely on computationally expensive architectures, complex training pipelines, or multimodal large language models. We present Pocket-STVG (P-STVG), a lightweight cascade architecture that addresses STVG by combining efficient pre-trained components instead of large end-to-end models. P-STVG integrates a temporal-aware video encoder based on MobileViCLIP, a spatial encoder-decoder derived from MDETR, and a shared aligned text encoder. Temporal localization is performed through either a lightweight 1D U-Net or a simple thresholding strategy, enabling the same framework to operate in both weakly supervised and zero-shot settings. Furthermore, video representations are precomputed independently of the query, yielding an indexing-friendly pipeline for efficient inference and large-scale video collections. Despite requiring fewer than 90M parameters, P-STVG performs on par with weakly supervised methods and improves on earlier zero-shot approaches at a fraction of their memory and computational cost, establishing a favorable performance-efficiency trade-off for STVG. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2609.31135 — 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 2026-10-08T01:12:14.536Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).