AndyTang15

Swin-Transformer

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

Deformable-ConvNets

Deformable Convolutional Networks

FCIS

Fully Convolutional Instance-aware Semantic Segmentation

Deep-Feature-Flow

Deep Feature Flow for Video Recognition

TimeCycle

Learning Correspondence from the Cycle-consistency of Time (CVPR 2019)

DynamicViT

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

ACTOR

Official Pytorch implementation of the paper "Action-Conditioned 3D Human Motion Synthesis with Transformer VAE", ICCV 2021

PixPro

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021

videowalk

Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)

st-resnet

Code release for "Spatiotemporal Residual Networks for Video Action Recognition", NIPS16 & "Spatiotemporal Multiplier Networks for Video Action Recognition", CVPR17.

UVC

Joint-task Self-supervised Learning for Temporal Correspondence (NeurIPS 2019)

transductive-vos.pytorch

a transductive approach for video object segmentation

annotation-tool

DMML

code for ICCV19 paper "Deep Meta Metric Learning"

annotations

ntds_2016

Material for the EPFL master course "A Network Tour of Data Science", edition 2016.

MTL-AQA

What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]

code

MUSDL