Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models
Zhixiang Wei (University of Science and Technology of China), Guangting Wang (Tencent (China)), Xiaoxiao Ma (University of Science and Technology of China), Ke Mei (Tencent (China)), Huaian Chen (University of Science and Technology of China), Yi Jin (University of Science and Technology of China), Fengyun Rao (Tencent (China))
IEEE/CVF International Conference on Computer Vision (ICCV)
DOI: 10.1109/iccv51701.2025.02084 (Computer Science)
Licence : non indiquée (tous droits réservés)
Publié le 19 Oct. 2025