Generative neural networks
Binding and Perspective Taking as Inference in a Generative Neural Network Model
Advances in Password Recovery using Generative Deep Learning Techniques
o 0886
Dilated Residual Aggregation Network for Text-guided Image Manipulation
Denoising AutoEncoder based Delete and Generate Approach for Text Style Transfer
GUIS2Code: A Computer Vision Tool to Generate Code Automatically from Graphical User Interface Sketches
Generating Math Word Problems from Equations with Topic Consistency Maintaining and Commonsense Enforcement
Generative properties of Universal Bidirectional Activation-based Learning
Graph neural networks I
Joint Graph Contextualized Network for Sequential Recommendation
Relevance-Aware Q-matrix Calibration for Knowledge Tracing
LGACN: A Light Graph Adaptive Convolution Network for Collaborative Filtering
HawkEye: Cross-Platform Malware Detection with Representation Learning on Graphs
An Empirical Study of the Expressiveness of Graph Kernels and Graph Neural Networks
Multi-resolution Graph Neural Networks for PDE approximation
Link Prediction on Knowledge Graph by Rotation Embedding on the Hyperplane in the Complex Vector Space
Graph neural networks II
Contextualise Entities and Relations: An Interaction Method for Knowledge Graph Completion
Civil Unrest Event Forecasting Using Graphical and Sequential Neural Networks
Parameterized Hypercomplex Graph Neural Networks for Graph Classification
Feature Interaction Based Graph Convolutional Networks For Image-text Retrieval
Generalizing Message Passing Neural Networks to Heterophily using Position Information
Local and Non-local Context Graph Convolutional Networks for Skeleton-based Action Recognition.-STGATP: A Spatio-temporal Graph Attention Network for Long-term Traffic Prediction
Hierarchical and ensemble models
Integrating N-Gram Features into Pre-Trained Model: A Novel Ensemble Model for Multi-Target Stance Detection
Hierarchical Ensemble for Multi-view Clustering
Structure-Aware Multi-Scale Hierarchical Graph Convolutional Network for Skeleton Action Recognition
Learning Hierarchical Reasoning for Text-based Visual Question Answering
Hierarchical Deep Gaussian Processes Latent Variable Model via Expectation Propagation
Adaptive Consensus-Based Ensemble for Improved Deep Learning Inference Cost
Human pose estimation
Multi-Branch Network for Small Human Pose Estimation
PNO: Personalized Network Optimization for Human Pose and Shape Reconstruction
JointPose: Jointly Optimizing Evolutionary Data Augmentation and Prediction Neural Network for 3D Human Pose Estimation
DeepRehab: Real Time Pose Estimation on the Edge for Knee Injury Rehabilitation
Image processing
Subspace constraint for Single Image Super-Resolution
Towards Fine-Grained Control over Latent Space for Unpaired Image-to-Image Translation
FMSNet: Underwater Image Restoration by Learning from a Synthesized Dataset
Towards Measuring Bias in Image Classification
Towards Image Retrieval with Noisy Labels via Non-deterministic Features
Image segmentation
Improving Visual Question Answering by Semantic Segmentation
Weakly Supervised Semantic Segmentation with Patch-Based Metric Learning Enhancement
ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation
Depth Mapping Hybrid Deep Learning Method for Optic Disc and Cup Segmentation on Stereoscopic Ocular Fundus
RATS: Robust Automated Tracking and Segmentation of Similar Instances
Knowledge distillation
Data Diversification Revisited: Why Does It Work?
A Generalized Meta-Loss Function for Distillation Based Learning Using Privileged Information for Classification and Regression
Empirical Study of Data-Free Iterative Knowledge Distillation
Adversarial Variational Knowledge Distillation
Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation
Medical image processing
Semi-supervised Learning based Right Ventricle Segmentation Using Deep Convolutional Boltzmann Machine Shape Model
Improved U-Net for Plaque Segmentation of Intracoronary Optical Coherence Tomography Images
Approximated Masked Global Context Network for Skin Lesion Segmentation
DSNet: Dynamic Selection Network for Biomedical Image Segmentation
Computational Approach to Identifying Contrast-Driven Retinal Ganglion Cells
Radiological Identification of Hip Joint Centers from X-ray Images Using Fast Deep Stacked Network and Dynamic Registration Graph
A Two-Branch Neural Network for Non-Small-Cell Lung Cancer Classification and Segmentation
Uncertainty Quantification and Estimation in Medical Image Classification
Labeling Chest X-Ray Reports Using Deep Learning.