This work introduces a scalable approach that uses CLIP models to automatically generate synthetic labeled datasets, significantly reducing the need for manual annotation and demonstrates that synthetic labeling with vision-language models could serve as a practical and effective approach for large-scale visual attribute extraction in e-commerce product catalogs.
This work introduces a two-stage LLM pipeline that first discovers a compact, ranked schema of purchase-discriminative attributes for each product category, then extracts their values from catalog text using a fine-tuned compact LLM (Qwen3-4B) with Hyper-Parallel Decoding (HPD).
Nikhita Vedula, Dushyanta Dhyani, Bryan Wang et al.· 0 citations
The findings confirm that combining hybrid ensemble learning with active learning offers an effective, lightweight, and cost-efficient alternative to purely transformer-based approaches, making it well-suited for real-world text classification tasks where labeled data are scarce or expensive.
A novel evaluation framework called Image2Text2Image is proposed, which leverages diffusion models, such as Stable Diffusion or DALL-E, for text-to-image generation, and does not rely on human-annotated reference cap-tions, making it a valuable tool for assessing image captioning models.
Jia-Hong Huang, Hongyi Zhu, Yixian Shen et al.· 0 citations
This work proposes 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.
Tong Wu, Ming Cheng, Jiazhen Hu et al.· 0 citations
This work proposes a two-step validation method that integrates a PLM block into the generative IE pipeline and thereby leverages LLMs' correction capability, discovering that such a validation task enhances LLM performance, particularly on the extraction of weakly expressed, low-salience entities that appear sparsely...
Yi-Sheng Hsu, Nermeen Abou Baker, U. Handmann· arXiv.org· 0 citations
This paper explores unsupervised TBPS, with only unlabeled images, and proposes GTR, a two-stage generation-then-retrieval framework for text-based person search, and contributes LargeFine-Person, a large-scale TBPS dataset with high-quality, fine-grained, and diverse textual annotations.
Mang Ye, Yucheng Ji, Yang Bai et al.· IEEE Transactions on Pattern...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
