2018 ECCV papers
- 1. Attribute
- 2. Classification
- 3. Detection
- 4. Recogntion
- 5. Alignment
- 6. Segmentation
- 7. Tracking
- 8. Model Compression
- 9. Re-Id & Retrieval
- Retrieval
- Re-identification
- 10. Deep Learning
- 10.1. Attention mechanism
- 10.2. Loss
- 10.3. Domain Adaptation
- 10.4. Multi-task Learning
- 11. Image Processing & Conventional CV
- 11.1. Deblurring
- 12. Others
1. Attribute
Understanding Degeneracies and Ambiguities in Attribute Transfer
Generative Adversarial Network with Spatial Attention for Face Attribute Editing
Deep Imbalanced Attribute Classification using Visual Attention Aggregation
Attribute-Guided Face Generation Using Conditional CycleGAN
Facial Expression Recognition with Inconsistently Annotated Datasets
Efficient Relative Attribute Learning using Graph Neural Networks
2. Classification
Deep Generative Models for Weakly-Supervised Multi-Label Classification
Grassmann Pooling for Fine-Grained Visual Classification
Joint & Progressive Learning from High-Dimensional Data for Multi-Label Classification
Selective Zero-Shot Classification with Augmented Attributes
Improving Fine-Grained Visual Classification using Pairwise Confusion
Spatial Pyramid Calibration for Image Classification
Learning to Navigate for Fine-grained Classification
3. Detection
Acquisition of Localization Confidence for Accurate Object Detection
Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
arallel Feature Pyramid Network for Object Detection
Deep Feature Pyramid Reconfiguration for Object Detection
Bi-box Regression for Pedestrian Detection and Occlusion Estimation
Context Refinement for Object Detection
Localization Recall Precision (LRP): A New Performance Metric for Object Detection
Object Detection with an Aligned Spatial-Temporal Memory
Quantization Mimic: Towards Very Tiny CNN for Object Detection
PyramidBox: A Context-assisted Single Shot Face Detector
DetNet: Design Backbone for Object Detection (Face++)
Graininess-Aware Deep Feature Learning for Pedestrian Detection
Learning Region Features for Object Detection (Jifeng Dai)
Zero-Shot Object Detection
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
Receptive Field Block Net for Accurate and Fast Object Detection
4. Recogntion
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
Pairwise Relational Networks for Face Recognition
Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
Face Recognition with Contrastive Convolution
Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data
5. Alignment
Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment
GridFace: Face Rectification via Learning Local Homography Transformations (Face++)
6. Segmentation
Affinity Derivation and Graph Merge for Instance Segmentation
Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
7. Tracking
Triplet Loss with Theoretical Analysis in Siamese Network for Real-Time Object Tracking
8. Model Compression
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Clustering Convolutional Kernels to Compress Deep Neural Networks
Constraints Matter in Deep Neural Network Compression
Coreset-Based Convolutional Neural Network Compression
9. Re-Id & Retrieval
Retrieval
A Modulation Module for Multi-task Learning with Applications in Image Retrieval
Product Quantization Network for Fast Image Retrieval
Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
A Zero-Shot Framework for Sketch based Image Retrieval
Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
Re-identification
Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification
Pose-Normalized Image Generation for Person Re-identification
Unsupervised Person Re-identification by Deep Learning Tracklet Association
ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
Domain Adaptation through Synthesis for Unsupervised Person Re-identification
Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identification
Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
Person Re-identification with Deep Similarity-Guided Graph Neural Network (Xiaogang Wang)
Robust Anchor Embedding for Unsupervised Video Re-Identification in the Wild
Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
Part-Aligned Bilinear Representations for Person Re-Identification
Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identification
Adversarial Open-World Person Re-Identification
10. Deep Learning
SkipNet: Learning Dynamic Execution in Residual Networks
10.1. Attention mechanism
Convolutional Block Attention Module
Connecting Gaze, Scene and Attention
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
Boosted Attention: Leveraging Human Attention for Image Captioning
Interpolating Convolutional Neural Networks Using Batch Normalization
10.2. Loss
Deep Metric Learning with Hierarchical Triplet Loss
Correcting the Triplet Selection Bias for Triplet Loss
10.3. Domain Adaptation
Partial Adversarial Domain Adaptation
Adversarial Open Set Domain Adaptation
10.4. Multi-task Learning
Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification
Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States
Focus on the Hard Things: Dynamic Task Prioritization for Multitask Learning
11. Image Processing & Conventional CV
A Closed-form Solution to Photorealistic Image Stylization
Single Image Highlight Removal with a Sparse and Low-Rank Reflection Model
Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal
Learning to Blend Photos
DeepIM: Deep Iterative Matching for 6D Pose Estimation
Deep Burst Denoising
11.1. Deblurring
Unsupervised Class-Specific Deblurring
Normalized Blind Deconvolution
Learning Data Terms for Image Deblurring
Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks
Deblurring Natural Image Using Super-Gaussian Fields
Learning Warped Guidance for Blind Face Restoration
12. Others
ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation
Does Haze Removal Help Image Classification?
DeepIM: Deep Iterative Matching for 6D Pose Estimation
Robust fitting in computer vision: easy or hard?
CornerNet: Detecting Objects as Paired Keypoints
Attention-based Ensemble for Deep Metric Learning
Learning Compression from limited unlabeled Data
How good is my GAN?
Attend and Rectify: a gated attention mechanism for fine-grained recovery
SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images
A Scalable Exemplar-based Subspace Clustering Algorithm for Class-Imbalanced Data
Progressive Neural Architecture Search
推薦閱讀：
