extreme-assistant / cv_resources

A curated list of resources dedicated to Face Recognition & Detection, OCR, Objection Detection, Gan, 3D, Motion Track & Pose Estimation, ReID, NAS, Recommentation, Model Scaling

@[TOC]

Awesome of Computer Vision Resources

A curated list of resources dedicated to Face Recognition & Detection, OCR, Objection Detection, Gan, 3D, Motion Track & Pose Estimation, ReID, NAS, Recommentation, Model Scaling. Any suggestions and pull requests are welcome.

• ReID
• Gan
• NAS
• SLAM
• Classification
• Recommendation & CTR
  • CTR
  • Recommendation
• Video Processing
  • Classification
  • Augumentation
• Building and Training
  • Optimizing
  • Constructure
  • Strategy
  • Evaluation
• Body Related
  • Face Detection
  • Face Alignment
  • Head Detection
  • Liveness Detection
  • 3D Face
• Data Processing
  • Super resolution
  • Synthesis
  • Image Translation
  • Date augmentaiton
• Objection Detection & Semantic
  • Objection Detection
  • Salient Object Detecion
  • Segmentation
• Model Compress and Accelerate
  • Pruning
  • Accelerating
• Motion & Pose
  • Pose Estimation
  • Pose Transfer
  • Motion Track
  • Action Recognition
  • Keypoint Detection
• Text Detection & Recognition
  • Detection
  • Recogination

ReID

• [2019-CVPR] Bags of Tricks and A Strong Baseline for Deep Person Re-identification(Baseline) paper code paper
• [2019-CVPR] Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-IdentificationRolling Back to Pre-trained Network for Person Re-Identification paper code
• [2019-CVPR] DBC: Dispersion based Clustering for Unsupervised Person Re-identification paper code
• [2019-CVPR] EANet: Enhancing Alignment for Cross-Domain Person Re-identification(***SOTA) paper code
• [2019-CVPR] High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection paper https://github.com/liuwei16/CSP
• [2019-CVPR] Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification paper code
• [2019-CVPR] MAR: Unsupervised Person Re-identification by Soft Multilabel Learning paper code
• [2019-CVPR] SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection(SOTA) paper
• [2018-BMVC] Deep Association Learning for Unsupervised Video Person Re-identification paper code

Gan

• [collection] Awesome Generative Adversarial Networks with tensorflow**code
• [framework] Implementations of a number of generative models GAN, VAE, Seq2Seq, VAEGAN, GAIA, Spectrogram Inversion in Tensorflow** code
• [2019-CVPR] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding paper code code-pytorch
• [2019-CVPR] StyleGan: Generator Inversion for Image Enhancement and Animation papercode
• [2018-ICLR] Progressive Growing of GANs for Improved Quality, Stability, and Variation paper code)

NAS

• [framework] An open source AutoML toolkit for neural architecture search and hyper-parameter tuning code
• [2019-CVPR] AutoGrow: Automatic Layer Growing in Deep Convolutional Networks paper code
• [2019-ar Xiv] MDENAS: Multinomial Distribution Learning for Effective Neural Architecture Search paper code
• [2019-CVPR] MnasNet: Platform-Aware Neural Architecture Search for Mobile paper code
• [2019-CVPR] Searching for A Robust Neural Architecture in Four GPU Hours paper code
• [2019-arXiv] Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization paper code
• [2019-CVPR] Dynamic Distribution Pruning for Efficient Network Architecture Search paper code

SLAM

• [ToolBox] OpenVSLAM: a Versatile Visual SLAM Framework code
• [2019-CVPR] AdaptForStereo: Learning to Adapt for Stereo paper code
• [2019-arXiv] DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction paper code
• [2019-CVPR] Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation paper code
• [2019-CVPR] Defusr: Learning Non-volumetric Depth Fusion using Successive Reprojections code
• [2019-CVPR] GA-Net: Guided Aggregation Net for End-to-end Stereo Matching paper code
• [2019-CVPR] MegaDepth: Learning Single-View Depth Prediction from Internet Photos paper
• [2019-CVPR] Neural Rerendering in the Wild paper code code
• [2019-CVPR] PyRobot: An Open-source Robotics Framework for Research and Benchmarking paper code
• [2019-CVPR] Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes(3D reconstruction) paper code
• [2019-CVPR] SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks paper
• [2019-CVPR] Taking a Deeper Look at the Inverse Compositional Algorithm(image alignment) paper code

Classification

• [ToolBox] Sandbox for training convolutional networks for computer vision (VGG,ResNet,PreResNet,ResNeXt,SENet,ResAttNet,SKNet,PyramidNet,
• DenseNet,BagNet,MSDNet,FishNet,SqueezeNet,SqueezeResNet,SqueezeNext,ShuffleNet,ShuffleNetV2,MENet,MobileNet,FD-MobileNet,MobileNetV2,MobileNetV3, Xception,InceptionV3,InceptionV4,InceptionResNetV2,PolyNet,NASNet-Mobile,PNASNet-Large,EfficientNet) code
• [ToolBox] Classification models trained on ImageNetcode code-keras
• [2019-CVPR] RepMet: Representative-based metric learning for classification and one-shot object detection paper
• [2018-CVPR] SENet: Squeeze-and-Excitation Networks(champion for imageNet) paper code code-caffe
• [2018-CVPR] FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction paper code

Recommendation & CTR

• [ToolBox] Implementation of Deep Learning based Recommender Algorithms with Tensorflow code
• [ToolBox] A framework for training and evaluating AI models on a variety of openly available dialogue datasets code
• [ToolBox] StarSpace: Embed All The Things! paper code
• [ToolBox] Modular and Extendible package of deep-learning based CTR models code
• [collection] Classic papers and resources on recommendation papers
• [collection] A collection of resources for Recommender Systems papers
• [collection] papers,datas,outline for recommendation code code

CTR

• [2019-arXiv] Deep Learning Recommendation Model for Personalization and Recommendation Systems(***CTR) paper code

Recommendation

• [2019-arXiv] Generative Adversarial User Model for Reinforcement Learning Based Recommendation System paper
• [2019-arXiv] Recent Advances in Diversified Recommendation paper
• [2017-arXiv] Training Deep AutoEncoders for Collaborative Filtering(***SOTA) paper code

Video Processing

Classification

• [2019-CVPR] Video Classification paper code
• [2019-CVPR] FastDVDnet: Towards Real-Time Video denoising Without Explicit Motion Estimation(denoising) paper code
• [2019-CVPR] Hallucinating Optical Flow Features for Video Classification paper code

Augumentation

• [2019-CVPR] DAVANet: Stereo Deblurring with View Aggregation(debluring) paper code
• [2019-CVPR] DVDnet: A Simple and Fast Network for Deep Video Denoising(***SOTA) paper code
• [2019-CVPR] Deep Flow-Guided Video Inpainting paper code
• [2019-CVPR] EDVR: Video Restoration with Enhanced Deformable Convolutional Networks paper code
• [2019-CVPR] FastDVDnet: Towards Real-Time Video denoising Without Explicit Motion Estimation(denoising) paper code
• [2019-CVPR] TecoGAN: Temporally Coherent GANs for Video Super-Resolution paper code
• [2018-XXXX] A Deep Learning based project for colorizing and restoring old images and video!(***) code

Building and Training

• [ToolBox] Pretrained EfficientNet, MobileNetV3 V2 and V1, MNASNet A1 and B1, FBNet, ChamNet, Single-Path NAS code

Optimizing

• [2019-CVPR] Aggregation Cross-Entropy for Sequence Recognition (The ACE loss function exhibits competitive performance to CTC) paper code
• [2019-CVPR] KL-Loss: Bounding Box Regression with Uncertainty for Accurate Object Detection paper code

Constructure

• [2019-CVPR] Pacnet: Pixel-Adaptive Convolutional Neural Networks(new net constructure) paper code
• [2019-CVPR] ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection paper

Strategy

• [Toolbox] A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning code
• [2019-CVPR]mixup: Bag of Freebies for Training Object Detection Neural Networks paper code
• [2019-CVPR] Improving Transferability of Adversarial Examples with Input Diversity paper code
• [2019-CVPR] RePr: Improved Training of Convolutional Filters paper
• [2018-CVPR] Fd-mobilenet: Improved mobilenet with a fast downsampling strategy paper code

Evaluation

• [2019-CVPR] TedEval: A Fair Evaluation Metric for Scene Text Detectors(***) paper code
• [2019-CVPR] Tools for evaluating and visualizing results for the Multi Object Tracking and Segmentation (MOTS) paper code

Body Related

• [collection] A curated list of related resources for hand pose estimation** code
• [collection] Face Benchmark and Dataset code
• [ToolBox] A face recognition solution on mobile device code

Face Detection

• [2019-CVPR] Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders paper
• [2019-CVPR] DSFD: Dual Shot Face Detector paper code
• [2019-CVPR] RetinaFace: Single-stage Dense Face Localisation in the Wild(***SOTA) paper code
• [2019-CVPR] PyramidBox++: High Performance Detector for Finding Tiny Face(***SOTA) paper code
• [2019-CVPR] SRN: Improved Selective Refinement Network for Face Detection(SOTA) paepr code

Face Alignment

• [2018-arXiv] Face Alignment: How far are we from solving the 2D & 3D Face Alignment problem paper code
• [2018-CVPR] Look at Boundary: A Boundary-Aware Face Alignment Algorithm paper code
• [2018-ECCV] Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network code

Head Detection

• [2018-arXiv] FCHD: Fast and accurate head detection in crowded scenes paper code

Liveness Detection

• [2019-CVPR] A Non-Intrusive Method of Face Liveness Detection Using Specular Reflection and Local Binary Patterns(Liveness Detection) paper
• [2019-CVPR] FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing(***Anti-spoofing) paper code
• [2019-CVPR] Liveness Detection Using Implicit 3D Features paper

3D Face

• [2019-CVPR] Disentangled Representation Learning for 3D Face Shape(3D face) paper code
• [2019-CVPR] Expressive Body Capture: 3D Hands, Face, and Body From a Single Image paper code
• [2019-CVPR] Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision paper code
• [2019-CVPR] Monocular Total Capture: Posing Face, Body and Hands in the Wild paper code
• [2019-CVPR] MVF-Net: Multi-View 3D Face Morphable Model Regression(face reconstructing) code

Data Processing

Super resolution

• [2019-CVPR] AdaFM: Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers(denoising) paper code
• [2019-arXiv] AWSRN: Lightweight Image Super-Resolution with Adaptive Weighted Learning Network paper code
• [2019-CVPR] Deep Learning for Image Super-resolution: A Survey paper
• [2019-CVPR] DPSR: Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels paper code
• [2019-CVPR] Meta-SR: A Magnification-Arbitrary Network for Super-Resolution paper code
• [2019-arXiv] PASSRnet: Learning Parallax Attention for Stereo Image Super-Resolution paper code
• [2019-CVPR] SRNTT: Image Super-Resolution by Neural Texture Transfer papercode
• [2019-CVPR] Towards Real Scene Super-Resolution with Raw Images paper
• [2018-CVPR] RCAN: Image Super-Resolution Using Very Deep Residual Channel Attention Networks paper code

Synthesis

• [collection] Awesome Generative Adversarial Networks with tensorflow**code
• [framework] Implementations of a number of generative models GAN, VAE, Seq2Seq, VAEGAN, GAIA, Spectrogram Inversion in Tensorflow** code
• [2019-CVPR] DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis paper github.com/NVlabs/SPADE)
• [2019-CVPR oral] GauGAN: Semantic Image Synthesis with Spatially-Adaptive Normalization paper code
• [2019-CVPR] MSGAN: Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis paper code
• [2019-arXiv] MSG-GAN: Multi-Scale Gradients GAN for more stable and synchronized multi-scale image synthesis paper code
• [2019-argXiv] Self-Attention Generative Adversarial Networks paper code
• [2019-CVPR] Shapes and Context: In-the-wild Image Synthesis & Manipulation(Image Synthesis) code code
• [2019-CVPR] STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing paper code
• [2018-CVPR] High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs paper code

Image Translation

• [2019-CVPR] Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation( ) paper code
• [2018-CVPR] CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks paper
• [2018-CVPR] Pix2pix: Image-to-Image Translation with Conditional Adversarial Networks paper code

Date augmentaiton

• [2019-CVPR] A Preliminary Study on Data Augmentation of Deep Learning for Image Classification paper
• [2019-CVPR] Further advantages of data augmentation on convolutional neural networks paper
• [2019-CVPR] Learning Data Augmentation Strategies for Object Detection paper
• [2019-CVPR] PSIS: Data Augmentation for Object Detection via Progressive and Selective Instance-Switching paper code
• [2019-CVPR] Wide-Context Semantic Image Extrapolation(expand image) paper code

Objection Detection & Semantic

• [ToolBox] A Simple and Versatile Framework for Object Detection and Instance Recognition code
• [ToolBox] Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch code
• [ToolBox] ObjectionDetection by yolov2, tiny yolov3, mobilenet, mobilenetv2, shufflenet(g2), shufflenetv2(1x), squeezenext(1.0-SqNxt-23v5), light xception, xception code
• [ToolBox] MMDetection: Open MMLab Detection Toolbox and Benchmark paper code
• [ToolBox] Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet) code code
• [ToolBox] Segmentation models with pretrained backbones code

Objection Detection

• [2019-CVPR] Activity Driven Weakly Supervised Object Detection code
• [2019-CVPR] CenterNet: Objects as Points paper(***) code
• [2019-CVPR] Cascade R-CNN：High Quality Object Detection and Instance Segmentation(***SOTA) paper code code-Caffe
• [2019-CVPR] CornerNet-Lite: Efficient Keypoint Based Object Detection(SOTA) paper code
• [2019-CVPR] DFPN: Efficient Object Detection Model for Real-Time UAV Applications paper code code-Caffe
• [2019-CVPR] Distilling Object Detectors with Fine-grained Feature Imitation code
• [2019-CVPR] ExtremeNet: Bottom-up Object Detection by Grouping Extreme and Center Points(***) paper code
• [2019-CVPR] FSAF: Feature Selective Anchor-Free Module for Single-Shot Object Detection(SOTA) paper
• [2019-CVPR] FoveaBox: Beyond Anchor-based Object Detector(SOTA) paper
• [2019-CVPR] FCOS: Fully Convolutional One-Stage Object Detection（***） paper code
• [2019-CVPR] Grid R-CNN Plus: Faster and Better paper code
• [2019-CVPR] Hybrid Task Cascade for Instance Segmentation paper code
• [2019-CVPR] Locating Objects Without Bounding Boxes(***crowd count) paper code
• [2019-CVPR] Learning Data Augmentation Strategies for Object Detection paper code
• [2019-CVPR] LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking paper code
• [2019-CVPR] PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud(***SOTA) paper code code-unofficial
• [2019-CVPR] TridentNet: Scale-Aware Trident Networks for Object Detection(***SOTA) paper code
• [2019-CVPR] NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection paper code
• [2019-CVPR] Region Proposal by Guided Anchoring paper code
• [2019-CVPR] SNIPER: Efficient Multi-Scale Training paper code
• [2019-CVPR] SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection(fast and low power) paper
• [2019-CVPR] ScratchDet: Training Single-Shot Object Detectors from Scratch paper code
• [2019-CVPR] YOLOv3+: Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors paper code
• [2018-ECCV] Acquisition of Localization Confidence for Accurate Object Detection paper code

Salient Object Detecion

• [Survey] Salient Object Detection: A Survey paper
• [2019-CVPR] A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision code
• [2019-CVPR] AFNet: Attentive Feedback Network for Boundary-aware Salient Object Detection code
• [2019-CVPR] A Simple Pooling-Based Design for Real-Time Salient Object Detection code
• [2019-CVPR] BASNet: Boundary-Aware Salient Object Detection paper code
• [2019-CVPR] Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection paper code
• [2019-CVPR] CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection paper code
• [2019-CVPR] Cascaded Partial Decoder for Fast and Accurate Salient Object Detection(***) code
• [2019-CVPR] LFNet: Light Field Saliency Detection with Deep Convolutional Networks paper code
• [2019-CVPR] Pyramid Feature Attention Network for Saliency detection(***) paper code
• [2019-CVPR] Shifting More Attention to Video Salient Objection Detection paper code

Segmentation

• [2019-CVPR oral] CLAN: Category-level Adversaries for Semantics Consistent paper code
• [2019-CVPR] BRS: Interactive Image Segmentation via Backpropagating Refinement Scheme(***) paper code
• [2019-CVPR] DFANet：Deep Feature Aggregation for Real-Time Semantic Segmentation(used in camera) paper code
• [2019-CVPR] DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency paper code
• [2019-CVPR] Domain Adaptation(reducing the domain shif) paper
• [2019-CVPR] ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation paper code
• [2019-CVPR oral] GLNet: Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Imagespaper code
• [2019-CVPR] Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth(***SOTA) paper code
• [2019-ECCV] ICNet: Real-Time Semantic Segmentation on High-Resolution Images paper code
• [2019-CVPR] LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation(***SOTA) paper code
• [2019-arXiv] LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation paper code
• [2019-CVPR] PTSNet: A Cascaded Network for Video Object Segmentation paper code
• [2019-CVPR] PPGNet: Learning Point-Pair Graph for Line Segment Detection paper code
• [2019-CVPR] Show, Match and Segment: Joint Learning of Semantic Matching and Object Co-segmentation paper code
• [2019-CVPR] Video Instance Segmentation paper code
• [2018-ECCV] BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation paper [code](https://

Model Compress and Accelerate

• [collection] Collection of recent methods on DNN compression and acceleration https://github.com/MingSun-Tse/EfficientDNNs
• [collection] A curated list of neural network pruning resources https://github.com/he-y/Awesome-Pruning
• [collection] model compression and acceleration research papers https://github.com/cedrickchee/awesome-ml-model-compression
• [TollBox] Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research code

Pruning

• [2019-CVPR] An Improved Trade-off Between Accuracy and Complexity with Progressive Gradient Pruning(Prune) paepr code
• [2019-ICML] EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper code code
• [2019-CVPR] FPGM: Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration paper code
• [2019-CVPR] Importance Estimation for Neural Network Pruning code

Accelerating

• [2019-CVPR] SKNet: Selective Kernel Networks paper code
• [2019-CVPR] SENet: Squeeze-and-Excitation Networkspaper code
• [2019-CVPR] ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection paper

Motion & Pose

Pose Estimation

• [2019-CVPR] AlphaPose: Real-Time and Accurate Multi-Person Pose Estimation&Tracking System paper code
• [2019-CVPR] CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark paper code
• [2019-CVPR] Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields(Oral) paper code
• [2019-CVPR] EpipolarPose: Self-Supervised Learning of 3D Human Pose using Multi-view Geometry paper code
• [2019-CVPR] Exploiting Temporal Context for 3D Human Pose Estimation in the Wild paper code
• [2019-CVPR] Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network(SOTA) paper code
• [2019-CVPR] Fast Human Pose Estimation(pytorch) paper code
• [2019-CVPR] High-Resolution Representation Learning for Human Pose Estimation(SOTA) paper code
• [2019-CVPR] Hand Shape and Pose Estimation from a Single RGB Image paper code
• [2019-CVPR] In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations paper
• [2019-CVPR] VideoPose3D: 3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training code
• [2019-CVPR] XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera paper

Pose Transfer

• [2019-CVPR] Dense Intrinsic Appearance Flow for Human Pose Transfer paper code

Motion Track

• [2019-CVPR] ATOM: Accurate Tracking by Overlap Maximization(***SOTA) paper code
• [2019-IEEE] FANTrack: 3D Multi-Object Tracking with Feature Association Network paper code
• [2019-CVPR] Joint Monocular 3D Vehicle Detection and Tracking(***) paper code
• [2019-CVPR] Leveraging Shape Completion for 3D Siamese Tracking paper code
• [2019-CVPR Oral] Graph Convolutional Tracking(SOTA) code
• [2019-arXiv] Instance-Aware Representation Learning and Association for Online Multi-Person Tracking paper
• [2019-Github] multi-people tracking (centerNet based person detector + deep sort algorithm with pytorch)(SOTA) code
• [2019-CVPR] PoseFix: Model-agnostic General Human Pose Refinement Network paper code
• [2019-CVPR Oral] Progressive Pose Attention Transfer for Person Image Generation paper code
• [2019-CVPR] PifPaf: Composite Fields for Human Pose Estimation paper code code
• [2019-CVPR] SemGCN: Semantic Graph Convolutional Networks for 3D Human Pose Regression paper code
• [2019-CVPR] MVPOSE: Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views(multi-person) paper code
• [2019-CVPR] SiamMask: Fast Online Object Tracking and Segmentation: A Unifying Approach(***SOTA) paper code
• [2019-CVPR] SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks(***SOTA) paper code

Action Recognition

• [2019-arXiv] VTN:Lightweight Network Architecture for Real-Time Action Recognitionpaper code

Keypoint Detection

• [2018-CVPR] OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation(***) code

Text Detection & Recognition

Detection

• [2019-CVPR] Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation paper
• [2019-CVPR] A Multitask Network for Localization and Recognition of Text in Images(end-to-end) paper
• [2019-CVPR] AFDM: Handwriting Recognition in Low-resource Scripts using Adversarial Learning(data augmentation) paper code
• [2019-CVPR] CRAFT: Character Region Awareness for Text Detection paper code
• [2019-CVPR] Data Extraction from Charts via Single Deep Neural Network(*) paper
• [2019-CVPR] E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text paper
• [2019-arXiv] FACLSTM: ConvLSTM with Focused Attention for Scene Text Recognition paper
• [2019-CVPR] Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes paper
• [2019-CVPR] PSENET: Shape Robust Text Detection with Progressive Scale Expansion Network paper
• [2019-CVPR] PMTD: Pyramid Mask Text Detector paper code
• [2019-CVPR] Spatial Fusion GAN for Image Synthesis (word Synthesis) [paper](https://arxiv.org/abs/1812.05840 code
• [2019-CVPR] Scene Text Detection with Supervised Pyramid Context Network paper
• [2019-arXiv] TextField: Learning A Deep Direction Field for Irregular Scene Text Detection paper code
• [2019-CVPR] Typography with Decor: Intelligent Text Style Transfer paper code
• [2019-CVPR] TIOU: Tightness-aware Evaluation Protocol for Scene Text Detection(new Evalution tool)paper code
• [2019-arXiv] MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition paper code
• [2019-CVPR] Scene Text Magnifier paper
• [2018-CVPR] Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks paper
• [2018-ECCV] Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes paper code
• [2018-AAAI] PixelLink: Detecting Scene Text via Instance Segmentation paper code
• [2018-CVPR] RRPN: Arbitrary-Oriented Scene Text Detection via Rotation Proposals paper code

Recogination

• [2019-CVPR] ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification paper code code
• [2019-CVPR] E2E-MLT: an Unconstrained End-to-End Method for Multi-Language Scene Text paper
• [2018-CVPR] FOTS: Fast Oriented Text Spotting With a Unified Network paper code