Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda

Repo for the Video Person Clustering dataset, and code for the associated paper

Official code for Conformer: Local Features Coupling Global Representations for Visual Recognition

This is an official implementation for "Self-Supervised Learning with Swin Transformers".

[CVPR 2021] PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation, (Oral, Best Paper Award Finalist)

[CVPR 2021] Body Meshes as Points.

[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

(CVPR 2021 Oral) Open World Object Detection

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Official PyTorch implementation of "IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos", CVPRW 2021 (Oral.)

Location-Sensitive Visual Recognition with Cross-IOU Loss

[CVPR 2021] Code for "Augmentation Strategies for Learning with Noisy Labels".

Make human motion capture easier.

[ICCV'21] Learning Spatio-Temporal Transformer for Visual Tracking

Transformer Tracking (CVPR2021)

Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)

[ICCV-2021] TransReID: Transformer-based Object Re-Identification

The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.

Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

HAKE-Action in PyTorch

D2Go is a toolkit for efficient deep learning

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

PyTorch implementation of Barlow Twins.