Litcius/Paper detail

VeCLIP: Improving CLIP Training via Visual-Enriched Captions

Zhengfeng Lai, Haotian Zhang, Bowen Zhang, Wentao Wu, Haoping Bai, Aleksei Timofeev, Xianzhi Du, Zhe Gan, Jiulong Shan, Chen‐Nee Chuah, Yinfei Yang, Meng Cao

2024Lecture notes in computer science12 citationsDOI

Topics & Concepts

Computer scienceTraining (meteorology)Artificial intelligenceComputer visionComputer graphics (images)MeteorologyPhysicsNatural Language Processing TechniquesSubtitles and Audiovisual MediaMultimodal Machine Learning Applications
VeCLIP: Improving CLIP Training via Visual-Enriched Captions | Litcius