wang-sucess Goto Github PK

3d-object-tracking-in-video

tracking object in video and reconstruction in 3D

3d_video_converter_for_vr_box

This is a simple python script which converts a 2D video to 3D video for VR boxes. It is all about our mind's judgment about the picture. As we see normally we need to make our mind believe that some things are away and some are close. That just can be done by modifying the 2D image and that's it.

aic2018_iamai

A multi-camera vehicle detection, tracking and re-identification system

alignedreid

Alignedreid＋+: Dynamically Matching Local Information for Person Re-Identification.

automatic-gifs

Automatic Gifs in Python with Mask R-CNN

awesome-hand-pose-estimation

Awesome work on hand pose estimation/tracking

awesome-human-pose-estimation

A collection of awesome resources in Human Pose estimation.

awesome-object-detection

Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

awesome-object-tracking

Object Tracking Algorithms Resources

awesome-scene-text-detection

Text detection papers collection.

awesome-semantic-segmentation

awesome-semantic-segmentation

background-separation-using-u-net

Using U-Net model to perform Image Segmentation on Carvana Image Masking Challenge Dataset

bat_offer

2019-2020年互联网公司高频重点面试题

cabbage

Unofficial Implementation of the paper: Multiple People Tracking by Lifted Multicut and Person Re-identification

caffe

Caffe: a fast open framework for deep learning.

chainer-mask-rcnn

Chainer Implementation of Mask R-CNN. (Training code to reproduce the original result is available.)

comparing-trajectory-clustering-methods

Comparing Different Clustering Methods and Similarity Metrics on Trajectory Datasets

competition

These are the game codes for machine learning.

deep-residual-matting

This repository is to implement Deep Image Matting with ResNet.

deepcc-local

DeepCC tracker with local-aware settings

deepclustering

Deep Clustering

deeplearning

深度学习入门教程&&看过的文章

deeplearning-500-questions

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为15个章节，近20万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

dg-net

CVPR2019 Joint Discriminative and Generative Learning for Person Re-identification

dual-fisheye-video-stitching

Dual fisheye video stitching

dukemtmc

dukemtmc-pose

Pedestrian Pose for DukeMTMC-reID (Python and Matlab API)

dukemtmceval

fisheye_camera_calibration

fully-convolutional-network-semantic-segmentation

Implementation of the paper Fully Convolutional Networks for Semantic Segmentation, used to segment a person from a background in an RGB image