owal-mike

Swin-Transformer

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

dino

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

EasyMocap

Make human motion capture easier.

TensorRT

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Swin-Transformer-Object-Detection

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

TimeSformer

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

NGT

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

OWOD

(CVPR 2021 Oral) Open World Object Detection

barlowtwins

PyTorch implementation of Barlow Twins.

d2go

D2Go is a toolkit for efficient deep learning

TransReID

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

ImageNet21K

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

Stark

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

Transformer-SSL

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

MOTR

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

TransT

Transformer Tracking (CVPR2021)

Conformer

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

PoseAug

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

calibration-framework

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

TransformerTrack

pit

HAKE-Action-Torch

HAKE-Action in PyTorch

STAM

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

TorchPQ

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

LSNet

Location-Sensitive Visual Recognition with Cross-IOU Loss

Augmentation-for-LNL

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

BMP

[CVPR 2021] Body Meshes as Points.

unimoco

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

Video_Person_Clustering

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

IntegralAction_RELEASE

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