dagshub/papers-with-everything

Machine Learning papers with code, data and models

        # Papers With Everything

Hacktoberfest is a month-long virtual festival of open source! Participants are giving back to the community by completing pull requests, participating in events, and donating to open-source projects. This project is part of Hacktoberfest, where participants enrich the Open Source Data Science domain by adding datasets and models to existing code repos.

What is DagsHub?

DagsHub is a centralized platform to host and manage machine learning projects including code, data, models, experiments, annotations, model registry, and more! DagsHub does the MLOps heavy lifting for its users. Every repository comes with configured S3 storage, an experiment tracking server, and an annotation workspace - all using popular open-source tools like MLflow, DVC, Git, and Label Studio.

Quick Start to Contribution

• Sign-up to Hacktoberfest & DagsHub.
• Join our Hacktoberfest Discord channel.
• Read the contribution guidelines.
• Create a Pull Requests on the Papers With Everything with the README of your DagsHub Project.

What does the DagsHub community contribute?

Promoting Open Source Data Science has always been a core value for us at DagsHub. We've promoted it in various ways, including sponsoring the Reproducibility Challenge by Papers with Code to make SOTA paper accessible to the ML community.

This year, we decided to combine the open source festival of Hacktoberfest and the Reproducibility Challenge to create THE Grand Festival of Open Source Data Science!

In this challenge, participants will connect repos from GitHub to DagsHub that host reproduced papers from NeurIPS, ICML, ICLR, ACL, EMNLP, CVPR, and ECCV, and add their datasets and model's weights to DagsHub Storage.

How to contribute?

• Claim a paper you wish to contribute from the SOTA 3D or object-detection papers (KUDOS to Papers With Code) by opening a new issue on the GitHub repository and name it after the paper. Please make sure that the paper wasn't claimed.
• Connect the paper’s repository from GitHub to DagsHub.
• Upload the data and model to its DagsHub storage.
• Add relevant tags to the repository and files.
• Add the following labels to the repository:
  • 3D Model / object detection
  • hacktoberfest
• In the GitHub papers-with-everything project:
  • Open a new branch named after the paper.
  • Add a directory named after the paper with its README file.
  • Commit and push the changes to GitHub.
  • Create a pull request on GitHub.
• Optional: Connect the DagsHub repo to Papers with Code.

papers-with-everything's Issues

Claim: Orthographic Feature Transform for Monocular 3D Object Detection

https://paperswithcode.com/paper/orthographic-feature-transform-for-monocular

Claim:- One-shot Face Reenactment

Paper :- https://arxiv.org/pdf/1908.03251.pdf

Claim: A Method for Detection of Small Moving Objects in UAV Videos

https://paperswithcode.com/paper/a-method-for-detection-of-small-moving

Claim: VT-LPR (Automatic Toll Tax Collection With Vehicle Type And License Plate Recognition Using Deep Learning)

Paper claimed

This issue aims to add the models and dataset from the paper: Vehicle and License Plate Recognition with Novel Dataset for Toll Collection.

CLAIM: YouTube-8M: A Large-Scale Video Classification Benchmark

Source: https://paperswithcode.com/paper/youtube-8m-a-large-scale-video-classification

No code-of-conduct.md

If you are willing I can add a code of conduct to this repo. If yes could you add a hacktoberfest label and assign this issue to me?

Claim :- End-to-End Optimization of Scene Layout

Paper :- https://arxiv.org/pdf/2007.11744v1.pdf

Claim: Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection

Link at Papers With Code

Claim - FaceNet: A Unified Embedding for Face Recognition and Clustering

Paper: https://arxiv.org/abs/1503.03832

Claim:- YOLOv3: An Incremental Improvement

Paper:-https://paperswithcode.com/paper/yolov3-an-incremental-improvement

Claim :- You Only Look Once: Unified, Real-Time Object Detection

Paper:- https://arxiv.org/pdf/1506.02640.pdf

Claim :- EGNet: Edge Guidance Network for Salient Object Detection

Paper:- https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhao_EGNet_Edge_Guidance_Network_for_Salient_Object_Detection_ICCV_2019_paper.pdf

Claim :- Neural Rays for Occlusion-aware Image-based Rendering

Paper:- https://arxiv.org/pdf/2107.13421

Claim :- A Light CNN for Deep Face Representation with Noisy Labels

Paper :- https://arxiv.org/pdf/1511.02683.pdf

Claim- Vehicle-Rear: A New Dataset to Explore Feature Fusion for Vehicle Identification Using Convolutional Neural Networks

Paper claim

This issue aims to add the following:

• dataset; and
• deep learning model

from the paper: Vehicle-Rear: A New Dataset to Explore Feature Fusion for Vehicle Identification Using Convolutional Neural Networks.

Claim :- Balanced and Hierarchical Relation Learning for One-shot Object Detection

Paper :- https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_Balanced_and_Hierarchical_Relation_Learning_for_One-Shot_Object_Detection_CVPR_2022_paper.pdf

Claim: YOLOX (a high-performance anchor-free YOLO exceeding yolov3~v5) with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported

Paper claimed

This issue aims to add the models from the paper: YOLOX.

License Plate Detection

Claim: Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline

https://paperswithcode.com/paper/towards-end-to-end-license-plate-detection

Claim: A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector

https://paperswithcode.com/paper/a-robust-real-time-automatic-license-plate

add SOTA three-dimensional object detection model (Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation)

Hi,
I'd like to contribute to this repository by adding the implementation details of the following 3D object detection model: CenterSnap

Could you please assign this issue to me?

Claim {RP} : Learning to Discover and Detect Objects

Implementation of the "Learning to Discover and Detect Objects" research paper.
https://arxiv.org/abs/2210.10774v1

CLAIM : DeepFlux for Skeletons in the Wild

In this i am going to connect repo DeepFlux with this project

Paper:- https://arxiv.org/pdf/1811.12608v1.pdf
Repository:- https://github.com/YukangWang/DeepFlux

Claim Facenet: A Unified Embedding for Face Recognition and Clustering

https://arxiv.org/abs/1503.03832

Claim: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation

Code for https://paperswithcode.com/paper/mulan-multitask-universal-lesion-analysis

Claim :- Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection

Paper:- https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_Contrast_Prior_and_Fluid_Pyramid_Integration_for_RGBD_Salient_Object_CVPR_2019_paper.pdf

Claim :- Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

Paper :- https://arxiv.org/pdf/1905.08233

Claim :- Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars

paper:- https://arxiv.org/pdf/2008.10174

Claim: Zero-Shot Instance Segmentation

Papers With Code

Dagshub not responding after clicking on connect repo

I was trying to connect the repo to dagshub but there is error. It is always showing the page took longer than expected to load. Attaching a screen shot.

Please let me know if this is an issue from my side or an internal server issue from GH or Dagshub. Thanks

Claim: Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs

https://paperswithcode.com/paper/reading-car-license-plates-using-deep

Claim :- pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis

Paper :- https://arxiv.org/pdf/2012.00926.pdf

Damaged Building Detection

Link: https://paperswithcode.com/task/damaged-building-detection

Towards End-to-end Car License Plate Location and Recognition in Unconstrained Scenarios

Claim :- View-GCN: View-based Graph Convolutional Network for 3D Shape Analysis

Paper :- https://openaccess.thecvf.com/content_CVPR_2020/papers/Wei_View-GCN_View-Based_Graph_Convolutional_Network_for_3D_Shape_Analysis_CVPR_2020_paper.pdf