🚀 A fast safe reinforcement learning library in PyTorch

lecture slides for Deepmind x UCL 2021 reinforcement learning course available in YouTbue

Papers for Video Anomaly Detection, released codes collection, Performance Comparision.

PyTorch implementation of YOLOv4

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

Official implementation of "Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM"

[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity

Implementation of the Confluence and Confluence NMS algorithms

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

Official implementation for "InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition"

Official implementation of NeurIPS'23 paper, Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

A web-based AI yoga trainer that provides real-time feedback to the yoga pose performed by the user.

📄 Awesome CV is LaTeX template for your outstanding job application

Representation Learning (RepL) Methods in Reinforcement Learning and Causal Inference

Policy Search for Model Predictive Control with Application to Agile Drone Flight

code for the paper Incremental Proximal Multi-Forecast Model Predictive Control

This is a code repository for training the IPMAN-R model and evaluating performance

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

Pessimistic Value Iteration for Multi-Task Data Sharing in Offline RL

International Conference on Artificial Intelligence and Statistics (AISTATS) 2024

Code of ICCV 2023 paper: "AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism"

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

code for CVPR'24 "AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents"

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

Code repository for the paper "On the Benefits of 3D Pose and Tracking for Human Action Recognition", (CVPR 2023)

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos