classical-paper-in-deep-learning/深度学习经典paper

CV

Classification

1. AlexNet：ImageNet Classification with Deep Convolutional Neural Networks
2. VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
3. Going Deeper with Convolutions
4. Densely Connected Convolutional Networks
5. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
6. Rethinking the Inception Architecture for Computer Vision
7. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
8. Deep Residual Learning for Image Recognition
9. Label-embedding for attribute-based classification
10. Image Super-Resolution Using Deep Convolutional Networks
11. bilinear cnn models for fine-grained visual recognition
12. xception deep learning with depthwise separable convolutions
13. A Review on Multi-Label Learning Algorithms
14. Wide Residual Networks
15. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
16. Scene Classification Via pLSA
17. XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
18. Semi-Supervised Classification with Graph Convolutional Networks

Segmentation

1. Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
2. Instance-aware Semantic Segmentation via Multi-task Network Cascades
3. ParseNet: Looking Wider to See Better
4. Pyramid Scene Parsing Network
5. Rethinking Atrous Convolution for Semantic Image Segmentation
6. Learning Deconvolution Network for Semantic Segmentation
7. Fully Convolutional Networks for Semantic Segmentation
8. RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
9. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
10. U-Net: Convolutional Networks for Biomedical Image Segmentation
11. Semantic Image Segmentation via Deep Parsing Network
12. Learning Deconvolution Network for Semantic Segmentation
13. Learning to Refine Object Segments
14. Simultaneous Detection and Segmentation
15. Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
16. Yet Another Survey on Image Segmentation: Region and Boundary Information Integration
17. Class-specific, top-down segmentation
18. Learning to segment object candidates
19. ParseNet: Looking Wider to See Better

Object Detection

1. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
2. DSSD : Deconvolutional Single Shot Detector
3. Feature Pyramid Networks for Object Detection
4. Focal Loss for Dense Object Detection
5. Mask R-CNN
6. SSD: Single Shot MultiBox Detector
7. You Only Look Once:Unified, Real-Time Object Detection
8. YOLO9000: Better, Faster, Stronger
9. Training Region-based Object Detectors with Online Hard Example Mining
10. R-FCN: Object Detection via Region-based Fully Convolutional Networks
11. Deep Feature Pyramid Reconfiguration for Object Detection
12. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
13. DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
14. Rich feature hierarchies for accurate object detection and semantic segmentation
15. Recurrent convolutional neural network for object recognition
16. Render for CNN: Viewpoint Estimation in Images Using CNNs Trained With Rendered 3D Model Views
17. Learning to See by Moving
18. FaceNet: A unified embedding for face recognition and clustering
19. Edge Boxes: Locating Object Proposals from Edges
20. Mining actionlet ensemble for action recognition with depth cameras
21. Action Recognition with Improved Trajectories
22. Joint Deep Learning for Pedestrian Detection
23. Unsupervised learning of models for object recognition
24. An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector
25. Learning a Sparse Representation for Object Detection
26. 3D object proposals for accurate object class detection
27. Fast R-CNN
28. DSSD: Deconvolutional Single Shot Detector

action recogination

1. Towards Understanding Action Recognition
2. P-CNN: Pose-Based CNN Features for Action Recognition
3. Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth Maps
4. Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

Text Dectection

1. Text Detection and Recognition in Imagery: A Survey
2. Reading Text in the Wild with Convolutional Neural Networks
3. Character-level convolutional networks for text classification

image interpretation

1. Long-term Recurrent Convolutional Networks for Visual Recognition and Description
2. Ask Your Neurons: A Neural-Based Approach to Answering Questions About Images
3. Deep visual-semantic alignments for generating image descriptions

ZSL/ZSD

1. Zero-Shot Learning by Convex Combination of Semantic Embeddings
2. Synthesized Classifiers for Zero-Shot Learning
3. Latent Embeddings for Zero-shot Classification
4. Zero-Shot Learning via Semantic Similarity Embedding
5. Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
6. Unsupervised Domain Adaptation for Zero-Shot Learning
7. Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation
8. Zero-shot recognition with unreliable attributes

Re-id

1. Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification
2. Person Re-Identification Using Kernel-Based Metric Learning Methods

Pose Estimation

1. Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

Video classification

1. Large-Scale Video Classification with Convolutional Neural Networks
2. Beyond short snippets: Deep networks for video classification

其他

1. Attention Is All You Need
2. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
3. Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling
4. Bidirectional recurrent neural networks
5. auto-encoding variational bayes
6. Visualizing and Understanding Convolutional Networks
7. Dynamic Routing Between Capsules
8. training region-based object detectors with online hard example mining
9. Deep Neural Decision Forests
10. Convolutional Channel Features
11. Dropout: a simple way to prevent neural networks from overfitting
12. Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
13. Conditional Random Fields as Recurrent Neural Networks
14. How transferable are features in deep neural networks?
15. Recurrent Models of Visual Attention
16. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
17. Continuous control with deep reinforcement learning
18. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
19. Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
20. Sequence Level Training with Recurrent Neural Networks
21. Stochastic Backpropagation and Approximate Inference in Deep Generative Models
22. Learning Rich Features from RGB-D Images for Object Detection and Segmentation
23. Gradient-based Hyperparameter Optimization through Reversible Learning