作者：胡孟
連結：https://zhuanlan.zhihu.com/p/43715653
來源：知乎
著作權歸作者所有。商業轉載請聯絡作者獲得授權，非商業轉載請註明出處。
 

感謝cvfoundation，提供了這麼優質的論文索引，之前CVPR、ICCV已經收錄在cvfoundation中，歷年論文也很方便檢索，從今年開始ECCV也正式收錄到了cvfoundation中，真是大家的福音（當然了，很多論文在沒有公佈該paper list之前大家就已經閱讀過了，而且paper list更新得比較晚，但我還是很開心的）；

我按照關鍵字搜了些自己比較感興趣的topics，今後有空可以好好學一下：

關鍵字：face、object、detect

1 face detection

1. Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks
2. PyramidBox: A Context-assisted Single Shot Face Detector

2 face recognition

1. Face Recognition with Contrastive Convolution
2. Visual Psychophysics for Making Face Recognition Algorithms More Explainable
3. Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
4. Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
5. The Devil of Face Recognition is in the Noise
6. Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
7. Pairwise Relational Networks for Face Recognition
8. From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data

3 object detection

3.1 目標檢測

1. CornerNet: Detecting Objects as Paired Keypoints
2. DetNet: Design Backbone for Object Detection
3. Zero-Shot Object Detection
4. Parallel Feature Pyramid Network for Object Detection
5. Deep Feature Pyramid Reconfiguration for Object Detection
6. Receptive Field Block Net for Accurate and Fast Object Detection
7. SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection
8. Weakly Supervised Region Proposal Network and Object Detection
9. Acquisition of Localization Confidence for Accurate Object Detection
10. Deep Regionlets for Object Detection
11. Context Refinement for Object Detection
12. Quantization Mimic: Towards Very Tiny CNN for Object Detection
13. Modeling Visual Context is Key to Augmenting Object Detection Datasets
14. Learning Region Features for Object Detection
15. SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network
16. Localization Recall Precision (LRP): A New Performance Metric for Object Detection

3.2 顯著性目標檢測

1. Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
2. Reverse Attention for Salient Object Detection
3. Contour Knowledge Transfer for Salient Object Detection

3.3 video級目標檢測

1. Object Detection in Video with Spatiotemporal Sampling Networks
2. Fully Motion-Aware Network for Video Object Detection
3. Unsupervised Hard Example Mining from Videos for Improved Object Detection
4. Video Object Detection with an Aligned Spatial-Temporal Memory
5. Dilated Pyramid Convolution and Deeper Bidirectional ConvLSTM for Video Salient Object Detection
6. Visual-Inertial Object Detection and Mapping

3.4 其他目標檢測

1. DOCK: Detecting Objects by transferring Common-sense Knowledge
2. TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
3. Linear Span Network for Object Skeleton Detection
4. The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
5. ML-LocNet: Improving Object Localization with Multi-view Learning Network
6. Zero-Annotation Object Detection with Web Knowledge Transfer
7. Self-produced Guidance for Weakly-supervised Object Localization

4 Pedestrian Detection

1. Bi-box Regression for Pedestrian Detection and Occlusion Estimation
2. Graininess-Aware Deep Feature Learning for Pedestrian Detection
3. Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
4. Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation
5. Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting

5 OCR

1. TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
2. Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
3. Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
4. Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes

6 something about face

1. Attribute-Guided Face Generation Using Conditional CycleGAN
2. Generative Adversarial Network with Spatial Attention for Face Attribute Editing
3. X2Face: A network for controlling face generation using images, audio, and pose codes
4. Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment
5. GridFace: Face Rectification via Learning Local Homography Transformations
6. Learning to Anonymize Faces for Privacy Preserving Action Detection

7 tracking

1. Triplet Loss in Siamese Network for Object Tracking
2. Distractor-aware Siamese Networks for Visual Object Tracking
3. TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
4. Online Multi-Object Tracking with Dual Matching Attention Networks
5. Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers
6. Collaborative Deep Reinforcement Learning for Multi-Object Tracking
7. Multi-object Tracking with Neural Gating Using Bilinear LSTM

8 interesting issues

1. Scenes-Objects-Actions: A Multi-Task, Multi-Label Video Dataset ---- SOA，場景、目標、動作資料集
2. Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection ---- 陰影檢測
3. Fighting Fake News: Image Splice Detection via Learned Self-Consistency ---- 與假新聞圖片的鬥爭
4. Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline ---- 車牌檢測 + 識別資料集