作者:胡孟
链接:https://zhuanlan.zhihu.com/p/43715653
来源:知乎
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。
感谢cvfoundation,提供了这么优质的论文索引,之前CVPR、ICCV已经收录在cvfoundation中,历年论文也很方便检索,从今年开始ECCV也正式收录到了cvfoundation中,真是大家的福音(当然了,很多论文在没有公布该paper list之前大家就已经阅读过了,而且paper list更新得比较晚,但我还是很开心的);
我按照关键字搜了些自己比较感兴趣的topics,今后有空可以好好学一下:
关键字:face、object、detect
1 face detection
- Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks
- PyramidBox: A Context-assisted Single Shot Face Detector
2 face recognition
- Face Recognition with Contrastive Convolution
- Visual Psychophysics for Making Face Recognition Algorithms More Explainable
- Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
- Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
- The Devil of Face Recognition is in the Noise
- Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
- Pairwise Relational Networks for Face Recognition
- From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data
3 object detection
3.1 目标检测
- CornerNet: Detecting Objects as Paired Keypoints
- DetNet: Design Backbone for Object Detection
- Zero-Shot Object Detection
- Parallel Feature Pyramid Network for Object Detection
- Deep Feature Pyramid Reconfiguration for Object Detection
- Receptive Field Block Net for Accurate and Fast Object Detection
- SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection
- Weakly Supervised Region Proposal Network and Object Detection
- Acquisition of Localization Confidence for Accurate Object Detection
- Deep Regionlets for Object Detection
- Context Refinement for Object Detection
- Quantization Mimic: Towards Very Tiny CNN for Object Detection
- Modeling Visual Context is Key to Augmenting Object Detection Datasets
- Learning Region Features for Object Detection
- SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network
- Localization Recall Precision (LRP): A New Performance Metric for Object Detection
3.2 显著性目标检测
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
- Reverse Attention for Salient Object Detection
- Contour Knowledge Transfer for Salient Object Detection
3.3 video级目标检测
- Object Detection in Video with Spatiotemporal Sampling Networks
- Fully Motion-Aware Network for Video Object Detection
- Unsupervised Hard Example Mining from Videos for Improved Object Detection
- Video Object Detection with an Aligned Spatial-Temporal Memory
- Dilated Pyramid Convolution and Deeper Bidirectional ConvLSTM for Video Salient Object Detection
- Visual-Inertial Object Detection and Mapping
3.4 其他目标检测
- DOCK: Detecting Objects by transferring Common-sense Knowledge
- TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
- Linear Span Network for Object Skeleton Detection
- The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
- ML-LocNet: Improving Object Localization with Multi-view Learning Network
- Zero-Annotation Object Detection with Web Knowledge Transfer
- Self-produced Guidance for Weakly-supervised Object Localization
4 Pedestrian Detection
- Bi-box Regression for Pedestrian Detection and Occlusion Estimation
- Graininess-Aware Deep Feature Learning for Pedestrian Detection
- Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
- Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation
- Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting
5 OCR
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
- Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
- Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
6 something about face
- Attribute-Guided Face Generation Using Conditional CycleGAN
- Generative Adversarial Network with Spatial Attention for Face Attribute Editing
- X2Face: A network for controlling face generation using images, audio, and pose codes
- Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment
- GridFace: Face Rectification via Learning Local Homography Transformations
- Learning to Anonymize Faces for Privacy Preserving Action Detection
7 tracking
- Triplet Loss in Siamese Network for Object Tracking
- Distractor-aware Siamese Networks for Visual Object Tracking
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
- Online Multi-Object Tracking with Dual Matching Attention Networks
- Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers
- Collaborative Deep Reinforcement Learning for Multi-Object Tracking
- Multi-object Tracking with Neural Gating Using Bilinear LSTM
8 interesting issues
- Scenes-Objects-Actions: A Multi-Task, Multi-Label Video Dataset ---- SOA,场景、目标、动作数据集
- Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection ---- 阴影检测
- Fighting Fake News: Image Splice Detection via Learned Self-Consistency ---- 与假新闻图片的斗争
- Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline ---- 车牌检测 + 识别数据集