[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

Insightface Keras implementation

Effective prompting for Large Multimodal Models like GPT-4 Vision or LLaVA. 🔥

Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition (CVPR2023)

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

Deepsort with yolo series. This project support the existing yolo detection model algorithm (YOLOv3, YOLOV4, YOLOV4Scaled, YOLOV5, YOLOV6, YOLOV7, YOLOX, YOLOR, PPYOLOE ).

This is an official implementation of our CVPR 2021 paper "Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression" (https://arxiv.org/abs/2104.02300)

✏️ Web-based image segmentation tool for object detection, localization, and keypoints

Code and models for the Action Recognition benchmark of Assembly101

VS Code extension for behavior tree modeling and visualization.

( NeurIPS 2020 ) Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation

A collection of datasets ready to use with TensorFlow

Keras pretrained models (VGG16, InceptionV3, Resnet50, Resnet152) + Transfer Learning for predicting classes in the Oxford 102 flower dataset

Official Implementation of TeachAugment: Data Augmentation Optimization Using Teacher Knowledge (CVPR2022, Oral)

Implementation of "With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition, BMVC, 2021" in PyTorch

Open source implementation of RAL 2022 "Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation"

[ICLR2022] CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

D2Go is a toolkit for efficient deep learning

Yolov5 TensorRT Implementations

Code for CVPR'21 paper "Learning Asynchronous and Sparse Human-Object Interaction in Videos".

Code for the CVPR'19 paper "Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos"