xueluli Goto Github PK

accel

Fast, high accuracy video segmentation framework (CVPR 2019 oral)

alsf

The initial codes for the ALSF algorithm (named JLSF in this repository for the moment) and the ALSF_L1 algorithm are included in this repository for reference. The refined one will be soon released in the future version.

awesome-material

awesome material

compact-bilinear-pooling

This is a re-implementation of t the 2016 cvpr paper "Compact Bilinear Pooling" for fine-grained image classification

convlstm_pytorch

Implementation of Convolutional LSTM in PyTorch.

corrflow

Self-supervised Learning for Video Correspondence Flow (BMVC 2019)

feelvos

FEELVOS implementation in PyTorch; FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation

gluon-cv

Gluon CV Toolkit

gsfl-net

jpcem

Collaborative Priors for Multi-view ATR

kernel-pooling

machine-learning-systems-design

A booklet on machine learning systems design with exercises

mdcnn

This is a re-implementation of the paper "SAR Automatic Target Recognition Based on Multiview Deep Learning Framework"

mug

Learning Video Object Segmentation from Unlabeled Videos (CVPR2020)

portrait-segmentation

Real-time portrait segmentation for mobile devices

pytorch_convolutional_rnn

PyTorch implementation of Convolutional Recurrent Neural Network

rfd-net

Implementation code for RFD-Net

spg-3dvs

The code for the proposed SPG-3DVS method used for 3D vessel segmentation

stm

Video Object Segmentation using Space-Time Memory Networks

temporal-segment-networks

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

temporal-shift-module

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

tf_pb_model_convert

Convert TF2.2 saved pb model directly to TF1.13 and TF1.15 for inferencing

timecycle

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

unet-zoo

A collection of UNet and hybrid architectures in PyTorch for 2D and 3D Biomedical Image segmentation

uvc

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