kjw0612/awesome-deep-vision

A curated list of deep learning resources for computer vision

awesome-deep-vision's Issues

Add Semantic Segmentation

Start from BoxSup

Please consider adding AI summer in blogs section.

Hey! Great work man.
If you want, you can add our blog: https://theaisummer.com/ in the corresponding section.
It would be highly appreciated.
Thanks in advance and congrats again.
N.A.

CRF-RNN website

CRF-RNN (Zheng et al, 2015) has a website now with demo and source code:

http://www.robots.ox.ac.uk/~szheng/crfasrnndemo

ICCV 2015 papers

제 gist -- https://gist.github.com/myungsub/c99ea6a60320d06d6812 -- 에 추가할 candidate 논문 list만 정리하고 있는데요,

논문이 너무 많네요ㅠㅠ 파트별로 나눠서 조금씩 살펴보면 좋을 것 같아요.

그리고 일단은 관련 논문들을 전부 다 추가할건데 나중에 개수가 너무 많아지면 리스트 중에서 선별해서 추가하는식으로 바뀌어야 할까요?

PS. 현재 [Papers] 부분에 분야별로 나눠져 있는걸 대분류-소분류 식으로 나눠보고 조만간 PR로 올려볼 계획이에요. 제목보고 나누기만 하는건데도 생각보다 시간이 오래 걸리네요...

explanatory images

papers to add

stereo matching CVPR 2015
visual tracking ICML 2015

Summary and commentary

Would be useful if each entry had a succinct summary of the paper and commentary from someone that has read it on why you should read it.

That would make this list a lot more useful.

Add an Expo e-commerce complete project

C-Shopping-RN APP

This is a complete App developed by React Native (Expo). It is a beautiful e-commerce shopping application.

Use technology

• React Native
• Redux Toolkit
• RTK Query
• Expo Router
  -NativeWind

App open source address: https://github.com/huanghanzhilian/c-shopping-rn
Full stack open source address: https://github.com/huanghanzhilian/c-shopping

《计算机视觉实战演练：算法与应用》GitHub开源中文电子书、源码、读者交流社区

L0CV 一种结合了代码、图示和HTML的在线学习媒介

L0CV is a new generation of computer vision open source online learning media, a cross-platform interactive learning framework integrating graphics, source code and HTML. the L0CV ecosystem — Notebook, Datasets, Source Code, and from Diving-in to Advanced — as well as the L0CV Hub.

• 📕 online book https://charmve.github.io/computer-vision-in-action
• GitHub https://github.com/Charmve/computer-vision-in-action

Can you add PyTorch to the list of frameworks?

Maintainer needed?

If you're still looking for a maintainer, I might be up for giving a hand. I'm currently looking into loads of papers, I might as well share them, and I guess it could also help me structure my own stuff well :)

Have you considered creating a curated list on curatedpapers.com

Please add this

Computer Vision Development Container:
https://github.com/joehoeller/NVIDIA-GPU-Tensor-Core-Accelerator-PyTorch-OpenCV

공개 코드 추가

희수야 deep vision 관련해서 Software부분에 공개 코드들 추가해줄래?

"Deep Learning Course – Nando de Freitas@Oxford" in Video section is outdated

Validate pull requests with Travis

Hello, I wrote a tool that can validate README links (valid URLs, not duplicate). It can be run when someone submits a pull request.

It is currently being used by

• https://github.com/vsouza/awesome-ios
• https://github.com/matteocrippa/awesome-swift
• https://github.com/dkhamsing/open-source-ios-apps

Examples

• https://travis-ci.org/matteocrippa/awesome-swift/builds/96526196 ok ✅
• https://travis-ci.org/matteocrippa/awesome-swift/builds/96722421 link redirected / rename 🔴
• https://travis-ci.org/dkhamsing/open-source-ios-apps/builds/96763135 bad link / project deleted 🔴
• https://travis-ci.org/dkhamsing/open-source-ios-apps/builds/95754715 dupe 🔴

If you are interested, connect this repo to https://travis-ci.org/ and add a .travis.yml file to the project.

See https://github.com/dkhamsing/awesome_bot for options, more information
Feel free to leave a comment 😄

Colorization papers

There is some recent work on colorizing monochrome images:
Colorful Image Colorization Richard Zhang, Phillip Isola, Alexei A. Efros, ECCV 2016
https://github.com/richzhang/colorization

Ryan Dahl
http://tinyclouds.org/colorize/

I'm not sure where should this go, or if there should be a separate section for it - I can submit a PR once you let me know

Broken link on Torch tutorial

Hey guys. Just to let you know you have a broken link here.

Keep up the good work.

Papers in human pose estimation

Could you add a list of papers in human pose estimation? I think this is an important topic which is useful for human activity recognition, human motion prediction and human dynamics modelling. There is also a new keypoints challenge for the human pose estimation task in MSCOCO.

Update VOC2012 standings table

Here is a screenshot of the latest VOC2012 standings:

Plans to update awesome-deep-vision

• Re-structure sections
• Add conferences - ICCV 2015, NIPS 2015, ICLR Submissions (Some candidates are here https://github.com/snucv/winterstudy/tree/master/Conference)
• Sort with two criteria
• Benchmark winners (mostly recent).
• Timeline (mostly seminal works). Imagine a timeline similar to a GitHub branch graph based on which paper extends which. Methodological categories can be identified.
• Add blogs or interesting links

Papers in Image Generation Section

I think, subsections of Image Generation section need refinements.
There are papers which purely use CNNs and RNNs. And there are papers based on generative models - Variational Autoencoders(VAE), Generative Adverserial Networks(GAN), Deep Autoregressive Networks(DARN) etc. Some recent works also present techniques of mixing these works (like VAE+GAN http://arxiv.org/abs/1511.05644).
It would be better to have fine subcategories.
I can work on it if it is seems fine.

License and contributing guidelines

See https://github.com/sindresorhus/awesome#license and https://github.com/sindresorhus/awesome/blob/master/contributing.md for inspiration.

404 on a link

https://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/research/gaze-based-human-computer-interaction/appearance-based-gaze-estimation-in-the-wild/

"Missing Page" for Microsoft (Deep Residual Learning) [Slide]

Update the link for Microsoft (Deep Residual Learning) [Slide] http://research.microsoft.com/en-us/um/people/kahe/ilsvrc15/ilsvrc2015_deep_residual_learning_kaiminghe.pdf
Getting the "Missing Page" alert upon redirection to the microsoft research website.

Restructuring the content

It feels like given the amount of existent resources, a lot of them with very high quality, the content should be restructured so it's easier to find what we need, or some kind of tool should be put in place.

A few ideas include:
Having each of the subsections as a separate file and the main README.md just linking there.
On each of the subsections add some additional layers.
For example

• Topic
  • Year
    • Conference Year
      • List of papers

Perhaps topic and then year would be enough, there probably wouldn't be that many papers on a particular topic at a given conference.

about translate contribute

Hello, we are Korean university students. This project is an area we are interested in, so we would like to contribute.
We want to contribute through the Korean translation of the project. Is it okay to contribute?

Is this still being maintained?

No updates in the past ~5 months despite several pending pull requests. Is this collection still being maintained?