热点
"跨模态检索" 相关文章
Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation
cs.AI updates on arXiv.org 2025-07-02T22:33:34.000000Z
Jina CLIP v2:多语言多模态的文本图像向量模型
Jina AI 2024-11-22T11:44:20.000000Z
Apple Releases 4M-21: A Very Effective Multimodal AI Model that Solves Tens of Tasks and Modalities
MarkTechPost@AI 2024-06-18T12:01:43.000000Z