New generation of CLIP with fine grained discrimination capability, ICML2025

基于Yolov5_DeepSort的物体计数器，可以统计车流或人流量等

Generating captions on image datasets using MiniGPT-v2

Source code of our AAAI 2024 paper "Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval"

Repository for VisualSem: a high-quality knowledge graph to support research in vision and language.

Gitter for GitHub - 可能是目前颜值最高的GitHub微信小程序客户端

project for codecademy