Code for CVPR22 paper: Exploring Structure-aware Transformer over Interaction Proposals for Human...

Code for CVPR23 paper: Learning to Generate Language-supervised and Open-vocabulary Scene Graph u...

PWC-Net for optical flow estimation. (Adapted for pytorch > 1.0 & Python 3 from the the official ...

Official implementation of the TMM'23 paper “End-to-End Video Scene Graph Generation with Tempora...

Grounded Language-Image Pre-training

基于大模型搭建的微信聊天机器人，同时支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/GLM-4/LinkA...

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

X-modaler is a versatile and high-performance codebase for cross-modal analytics(e.g., image capt...