Search Results for author: Huixin Xiong

Found 1 papers, 0 papers with code

Injecting Image Details into CLIP's Feature Space

no code implementations31 Aug 2022 Zilun Zhang, Cuifeng Shen, Yuan Shen, Huixin Xiong, Xinyu Zhou

Although CLIP-like Visual Language Models provide a functional joint feature space for image and text, due to the limitation of the CILP-like model's image input size (e. g., 224), subtle details are lost in the feature representation if we input high-resolution images (e. g., 2240).

Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.