huizhang0110 / papers_in_cv

A papers list in computer vision fields.

A papers list in computer vision field

• Recent Advances in Deep Learning for Object Detection

reading iccv2019 papers

Text Detection

Text Recognition

• Symmetry-constrained Rectification Network for Scene Text Recognition

End2End

• Towards Unconstrained End-to-End Text Spotting

others

• SlowFast Networks for Video Recognition

reading cvpr2019 papers

• papers list

Text Detection

• Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation

• Learning Shape-Aware Embedding for Scene Text Detection

Text Recognition

• Sequence to Sequence Domain Adaptation Network for Robust Text Image Recognition

• ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification

• Aggregation Cross-Entropy for Sequence Recognition

Detection

• CSPnet keras

reading AAAI2019 papers

• papers list

Text Detection

Text Recognition

• Scene Text Recognition from Two-Dimensional Perspective

• Show, attend and read: a simple and strong baseline for recognising irregular text

Scene Text Recognition

• Aggregation Cross-Entropy for Sequence Recognition

• Edit Probability fro Scene Text Recognition CVPR2018

• AON: Towards Arbitrarily-Oriented Text Recognition CVPR2018 tensorflow-code

• SqueezedText: A Real-Time Scene Text Recognition by Binary Convolutional Encoder-Decoder Network AAAI2018

• Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition AAAI2018

• Enhancing RNN Based OCR by Transducative Transfer Learning From Text to Images AAAI2018

• ASTER: An Attentional Scene Text Recognizer with Flexible Rectification PAMI2018 tensorflow-code variable-length version

• Radical analysis network for zero-shot learning in printed Chinese character recognition

ICME2018

• Scene Text Recognition from Two-Dimensional Perspective

• A Novel Approach to On-Line Handwriting Recognition Based on Bidirectional Long Short-Term Memory Networks ICDAR2007

• Similar handwritten Chinese characters recognition by critical region selection based on average symmetric uncertainty ICFHR2010

• Synthetically Supervised Feature Learning for Scene Text Recognition ECCV2018

Scene Text Detection

• Detecting Text in Natural Image with Connectionist Text Proposal Network ECCV2016 code

• EAST: An Efficient and Accurate Scene Text Detector CVPR2017 tensorflow-code

• Detecting Oriented Text in Natural Images by Linking Segments CVPR2017 tensorflow-code

• Rotation-Sensitive Regression for Oriented Scene Text Detection CVPR2018

• Learning Markov Clustering Networks for scene Text Detection CVPR2018

• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation CVPR2018

• geometry-aware scene text detection with instance transformation network CVPR2018

• Feature Enhancement Network: A Refined Scene Text Detector AAAI2018

• PixelLink: Detecting Scene Text via Instance Segmentation AAAI2018 tensorflow-code

• IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection IJCAI2018

• TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes ECCV2018

• Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping ECCV2018

End2End Scene Text Spotting

• FOTS: Fast Oriented Text Spotting with a Unified Network CVPR2018

• SEE: Towards Semi-Supervised End-to-End Scene Text Recognition AAAI2018

• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes ECCV2018

• Using Object Information for Spotting Text ECCV2018

Scene Text Image Synthesis

• Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes ECCV2018

Scene Text Image Retrieval

• Image Retrieval using Textual Cues ICCV2013

• Single Shot Scene Text Retrieval ECCV2018 tensorflow-code

OCR others

• Visual Text Correction ECCV2018

• DocUNet: Document Image Unwarping via A Stacked U-Net CVPR2018

Object Detection

General object detection

• Soft-NMS -- Improving Object Detection With One Line of Code ICCV2017

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks NIPS2015 tensorflow-code

• Mask R-CNN ICCV2017 tensorflow-code

• SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network ECCV2018

• Reverse Attention for Salient Object Detection ECCV2018

• DetNet: Design Backbone for Object Detection ECCV2018

• Visual-Inertial Object Detection and Mapping ECCV2018

• Zero-Shot Object Detection ECCV2018

• Contour Knowledge Transfer for Salient Object Detection ECCV2018

• Fast and Accurate Intrinsic Symmetry Detection ECCV2018

• Weakly Supervised Region Proposal Network and Object Detection ECCV2018

• Zero-Annotation Object Detection with Web Knowledge Transfer ECCV2018

• Fully Motion-Aware Network for Video Object Detection ECCV2018

• Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection ECCV2018

• Deep Feature Pyramid Reconfiguration for Object Detection ECCV2018

• Receptive Field Block Net for Accurate and Fast Object Detection ECCV2018

• SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images ECCV2018

• Parallel Feature Pyramid Network for Object Detection ECCV2018

• TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection ECCV2018

• SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection ECCV2018

• Acquisition of Localization Confidence for Accurate Object Detection ECCV2018

• Localization Recall Precision (LRP): A New Performance Metric for Object Detection ECCV2018

• Deep Regionlets for Object Detection ECCV2018

• Quantization Mimic: Towards Very Tiny CNN for Object Detection ECCV2018

GAN

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks ICLR 2016

• Image-to-Image Translation with Conditional Adversarial Networks CVPR 2017

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks ICCV2017

Logo Detection

Person Re-Identification

• AlignedReID: Surpressing Human-Level Performance in Person Re-Identification tensorflow-code

• Beyond Part Models: Person Retrieval with Refined Part Pooling

• Improving Person Re-identification by Attribute and Identity Learning

• Bi-box Regression for Pedestrian Detection and Occlusion Estimation ECCV2018

CNN base

• Deep Residual Learning for Image Recognition CVPR2016

• Identity Mappings in Deep Residual Networks ECCV2016

• Aggregated Residual Transformations for Deep Neural Networks CVPR2017

Others

• Spatial Transformer Networks NIPS2015 code

• Squeeze-and-Excitation Networks

• Deep Binary Representation for Efficient Image Retrieval

• Sequential Context Encoding for Duplicate Removal NIPS2018

• Training Region-based Object Detectors with Online Hard Example Mining CVPR2016