Neural Information Processing: 28th International Conference, ICONIP 2021, Sanur, Bali, Indonesia, December 8-12, 2021, Proceedings, Part III

Cognitive Neurosciences.- A Novel Binary BCI Systems Based on Non-oddball Auditory and Visual Paradigms.- A Just-In-Time Compilation Approach for Neural Dynamics Simulation.- STCN-GR: Spatial-Temporal Convolutional Networks for Surface-Electromyography-Based Gesture Recognition.- Gradient descent learning algorithm based on spike selection mechanism for multilayer spiking neural networks.- Learning to Coordinate via Multiple Graph Neural Networks.- A Reinforcement Learning Approach for Abductive Natural Language Generation.- DFFCN: Dual Flow Fusion Convolutional Network for Micro Expression Recognition.- AUPro: Multi-label Facial Action Unit Proposal Generation for Sequence-level Analysis.- Deep kernelized network for fine-grained recognition.- Semantic Perception Swarm Policy with Deep Reinforcement Learning.- Reliable, Robust, and Secure Machine Learning Algorithms Open-Set Recognition with Dual Probability Learning.- How Much Do Synthetic Datasets Matter In Handwritten Text Recognition.- PCMO: Partial Classification from CNN-Based Model Outputs.- Multi-branch Fusion Fully Convolutional Network for Person Re-Identification.- Fast Organization of Objects Spatial Positions in Manipulator Space from Single RGB-D Camera.- EvoBA: An Evolution Strategy as a Strong Baseline for Black-Box Adversarial Attacks.- A Novel Oversampling Technique for Imbalanced Learning Based on SMOTE and Genetic Algorithm.- Dy-Drl2Op: Learning Heuristics for TSP on the Dynamic Graph via Deep Reinforcement Learning.- Multi-label classification of hyperspectral images based on label-specific feature fusion.- A Novel Multi-Scale Key-Point Detector Using Residual Dense Block and Coordinate Attention.- Alleviating Catastrophic Interference in Online Learning via Varying Scale of Backward Queried Data.- Construction and Reasoning for Interval-Valued EBRB Systems.- Theory and Applications of Natural Computing Paradigms.- Brain-mimetic Kernel: A Kernel Constructed from Human fMRI Signals Enabling a Brain-mimetic Visual Recognition Algorithm.- Predominant Sense Acquisition with a Neural Random Walk Model.- Processing-response dependence on the on-chip readout positions in spin-wave reservoir computing.- Advances in deep and shallow machine learning algorithms for biomedical data and imaging.- A Multi-Task Learning Scheme for Motor Imagery Signal Classification.- An End-to-End Hemisphere Discrepancy Network for Subject-Independent Motor Imagery Classification.- Multi-domain Abdomen Image Alignment Based on Joint Network of Registration and Synthesis.- Coordinate Attention Residual Deformable U-Net for Vessel Segmentation.- Gated Channel Attention Network for Cataract Classification on AS-OCT Image.- Overcoming Data Scarcity for Coronary Vessel Segmentation Through Self-Supervised Pre-Training.- Self-Attention Long-Term Dependency Modelling in Electroencephalography Sleep Stage Prediction.- ReCal-Net: Joint Region-Channel-Wise Calibrated Network for Semantic Segmentation in Cataract Surgery Videos.- Enhancing Dermoscopic Features Classification in Images Using Invariant Dataset Augmentation and Convolutional Neural Networks.- Ensembles of Randomized Neural Networks for Pattern-based Time Series Forecasting.- Grouped Echo State Network with Late Fusion for Speech Emotion Recognition.- Applications.- MPANet: Multi-level Progressive Aggregation Network for Crowd Counting.- AFLLC: A Novel Active Contour Model based on Adaptive Fractional Order Differentiation and Local Linearly Constrained Bias Field.- DA-GCN: A Dependency-Aware Graph Convolutional Network for Emotion Recognition in Conversations.- Semi-Supervised Learning with Conditional GANs for Blind Generated Image Quality Assessment.- Uncertainty-Aware Domain Adaptation for Action Recognition.- Free-Form Image Inpainting with Separable Gate Encoder-decoder Network.- BERTDAN: Question-Answer Dual Attention Fusion Networks With Pre-trained Models for Answer Selection.- Rethinking the Effectiveness of Selective A