Metraipolis › archive › dc_150698d0433d

Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos — arXiv:2609.06410

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06410
License (as archived)
CC0-1.0
Archived
2026-10-16T12:45:07.334Z
SHA-256 of the archived text
9380c395a10bbcf83f90890c9a8ac64bce416ff54092f9c2c6627e9e1fdd4682
Stable URL of this page
https://metraipolis.com/documento/dc_150698d0433d

How to cite

Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos — arXiv:2609.06410 — arXiv (en), https://arxiv.org/abs/2609.06410 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_150698d0433d (Metraipolis archive dc_150698d0433d, sha256 9380c395a10bbcf83f90890c9a8ac64bce416ff54092f9c2c6627e9e1fdd4682)
BibTeX
@misc{dc150698d0433d,
  title = {Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos — arXiv:2609.06410},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06410},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_150698d0433d; sha256 9380c395a10bbcf83f90890c9a8ac64bce416ff54092f9c2c6627e9e1fdd4682},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06410. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing approaches to visual attribute value extraction (AVE) primarily rely on static product images, failing to capture temporal cues, multi-angle views and fine-grained visual details. Directly applying video vision-language models (VLMs) to product AVE results in limited performance due to the lack of domain knowledge, and fine-tuning them requires extensive high-quality data and substantial computational resources. Thus, we propose visual search augmented chain-of-thought reasoning (ViS-CoT), a training-free, plug-and-play pipeline that can be easily applied to any open-source video VLM for video-to-text AVE in e-Commerce. Specifically, ViS-CoT employs visual clustering to identify representative frames, followed by visual search to retrieve semantically similar product knowledge that can enrich attribute cues. Next, an interleaved CoT reasoning module iteratively refines reasoning through visually-aligned auxiliary texts derived from captioning and automatic speech recognition. Finally, the integrated information guides the model toward accurate and fine-grained attribute predictions. Extensive experiments across 14 product categories on the VideoAVE dataset show that ViS-CoT consistently enhances multiple state-of-the-art video VLMs, achieving an average improvement of 17.91 percentage points in micro-F1.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.06410 — 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 2026-10-16T12:30:25.036Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).