Neural Information Processing 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, December 12–15, 2019, Proceedings, Part II

The three-volume set of LNCS 11953, 11954, and 11955 constitutes the proceedings of the 26th International Conference on Neural Information Processing, ICONIP 2019, held in Sydney, Australia, in December 2019.

The 173 full papers presented were carefully reviewed and selected from 645 submissions. The papers address the emerging topics of theoretical research, empirical studies, and applications of neural information processing techniques across different domains. The second volume, LNCS 11954, is organized in topical sections on image processing by neural techniques; learning from incomplete data; model compression and optimisation; neural learning models; neural network applications; and social network computing.

Image Processing by Neural Techniques.- STNet: A Style Transformation Network for Deep Image Steganography.- Multi-person 3D Pose Estimation  from Monocular Image Sequences.- Super-Resolution Network for General Static Degradation Model.- Feature Combination Based on Receptive Fields and Cross-Fusion Feature Pyramid for Object Detection.- Multi-scale Information Distillation Network for Image Super Resolution in NSCT Domain.- Image Denoising Networks with Residual Blocks and RReLUs.- Shape Description and Retrieval in a Fused Scale Space.- Only Image Cosine Embedding For Few-shot Learning.- Deep 3D Segmentation and Classification of Point Clouds for Identifying AusRAP Attributes.- A Robustness and Low Bit-rate Image Compression Network for Underwater Acoustic Communication.- Gated Contiguous Memory U-Net for Single Image Dehazing.- Combined Correlation Filters With Siamese Region Proposal Network For Visual Tracking.- RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments.- A Novel Image-Based Malware Classification Model Using Deep Learning.- Visual Saliency Detection via Convolutional Gated Recurrent Units.- RBPNET:An asymptotic residual back-projection network for super resolution of very low resolution face image.- Accurate Single Image Super-Resolution using Deep Aggregation Network.- Reinforcing LiDAR-Based 3D Object Detection with RGB and 3D Information.- Cross-View Image Retrieval - Ground to Aerial Image Retrieval through Deep Learning.- Direct Image to Point Cloud Descriptors Matching for 6-DOF Camera Localization in Dense 3D Point Clouds.- Learning from Incomplete Data.- Improving Object Detection with Consistent Negative Sample Mining.- A model selection criterion for LASSO estimate with scaling.- Geometric mean metric learning for label distribution learning.- Explicit Center Selection and Training for Fault Tolerant RBF Networks.- Learning with Incomplete Labels for Multi-label Image Annotation using CNN and Restricted Boltzmann Machines.- Learning-Based Confidence Estimation for Multi-Modal Classifier Fusion.- Model Compression and Optimisation.- Siamese Network for Classification with Optimization of AUC.- Attention-based Audio-visual Fusion for Video Summarization.- RLDR-Pruning: Restricted Linear Dimensionality Reduction Approach for Model Compression.- Adaptive Neuro-Surrogate-Based Optimization Method for Wave Energy Converters Placement Optimization.- Lightweighted Modal Regression for stand alone embedded systems.- Sparse Modeling of Nonlinear Dynamics in Heterogeneous Reactions.- Neural Learning Models.- Sparse Least Squares Low Rank Kernel Machines.- Proposal of online regularization for dynamical structure optimization in complex-valued neural networks.- Set Aggregation Network as a Trainable Pooling Layer.- Exploring Latent Structure Similarity for Bayesian Nonparameteric Model with Mixture of NHPP Sequence.- Conditionally Decorrelated Multi-Target Regression.- Local Near-optimal Control for Interconnected Systems with Time-varying Delays.- Neural Network Applications.- Transferring Tree Ensembles to Neural Networks.- Neuro-inspired System with Crossbar Array of Amorphous Metal-Oxide-Semiconductor Thin-Film Devices as Self-Plastic Synapse Units - Letter Recognition of Five Alphabets.- Barrier Function Based Consensus of High-order Nonlinear Multi-agent Systems With State Constraints.- Transformer-DW: A Transformer Network with Dynamic and Weighted Head.- Motion-based Occlusion-aware Pixel Graph Network for Video Object Segmentation.- Modeling Severe Traffic Accidents with Spatial and Temporal Features.- Sparse Dynamic Binary Neural Networks for Storage and Switching of Binary Periodic Orbits.- IMDB-Attire: A Novel Dataset for Attire Detection and Localization.- From Raw Signals to Human Skills Level in Physical Human-Robot Collaboration for Advanced-Manufacturing Applications.- Intelligent Image Retrieval Based on Multi-swarm of Particle Swarm Optimization and Relevance Feedback.- Achieving Human–Robot Collaboration with Dynamic Goal Inference by Gradient Descent.- Neuromuscular Activation Based SEMG-Torque Hybrid Modeling and Optimization for Robot Assisted Neurorehabilitation.- Social Network Computing.- Secure Outsourcing of Lattice Basis Reduction.- DARIM: Dynamic Approach for Rumor Influence Minimization in Online Social Networks.- SRRL: Select Reliable Friends for Social Recommendation with Reinforcement Learning.- Aspect-Level Sentiment Classification with Dependency Rules and Dual Attention.- Aligning users across Social Networks by Joint User And Label Consistence Representation.- Opinion Knowledge Injection Network for Aspect Extraction.- A Deep Matrix Factorization Method with Missing Not at Random Data for Social Recommendation.- Pluralistic Ignorance: a trade off between group-conformity and cognitive dissonance.