Industry leading face manipulation platform

[AAAI 2025] VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding

Instantly create video clips from LLM prompts

WebUI extension for ControlNet

Official repository of Agent Attention (ECCV2024)

A toolbox of ocr models and algorithms based on MindSpore

Official PyTorch implementation of IEEE Transaction on Multimedia 2023 paper “DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition” .

This is the official PyTorch implementation of ASAG (ICCV 2023).

The code for CVPR2022 paper "Likert Scoring with Grade Decoupling for Long-term Action Assessment".

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners