The four-volume proceedings LNCS 13108, 13109, 13110, and 13111 constitutes the proceedings of the 28th International Conference on Neural Information Processing, ICONIP 2021, which was held during December 8-12, 2021. The conference was planned to take place in Bali, Indonesia but changed to an online format due to the COVID-19 pandemic.
The total of 226 full papers presented in these proceedings was carefully reviewed and selected from 1093 submissions. The papers were organized in topical sections as follows:
Part I: Theory and algorithms;
Part II: Theory and algorithms; human centred computing; AI and cybersecurity;
Part III: Cognitive neurosciences; reliable, robust, and secure machine learning algorithms; theory and applications of natural computing paradigms; advances in deep and shallow machine learning algorithms for biomedical data and imaging; applications;
Part IV: Applications.
Inhaltsverzeichnis
Theory and Algorithms. - Metric Learning Based Vision Transformer for Product Matching. - Stochastic Recurrent Neural Network for Multistep Time Series Forecasting. - Speaker Verification with Disentangled Self-Attention. - Multi Modal Normalization. - A Focally Discriminative Loss for Unsupervised Domain Adaptation. - Automatic Drum Transcription with Label Augmentation using Convolutional Neural Networks. - Adaptive Curriculum Learning for Semi-Supervised Segmentation of 3D CT-Scans. - Genetic Algorithm and Distinctiveness Pruning in the Shallow Networks for VehicleX. - Stack Multiple Shallow Autoencoders into A Strong One: A New Reconstruction-based Method to Detect Anomaly. - Learning Discriminative Representation with Attention and Diversity for Large-scale Face Recognition. - Multi-task Perceptual Occlusion Face Detection with Semantic Attention Network. - RAIDU-Net: Image Inpainting via Residual Attention Fusion and Gated Information Distillation. - Sentence Rewriting with Few-Shot Learningfor Document-Level Event Coreference Resolution. - A Novel Metric Learning Framework for Semi-supervised Domain Adaptation. - Generating Adversarial Examples by Distributed Upsampling. - CPSAM: Channel and Position Squeeze Attention Module. - A Multi-Channel Graph Attention Network for Chinese NER. - GSNESR: A Global Social Network Embedding Approach for Social Recommendation. - Classification Models for Medical Data with Interpretative Rules. - Contrastive Goal Grouping for Policy Generalization in Goal-Conditioned Reinforcement Learning. - Global Fusion Capsule Network with Pairwise-Relation Attention Graph Routing. - MA-GAN: A Method Based on Generative Adversarial Network for Calligraphy Morphing. - One-Stage Open Set Object Detection with Prototype Learning. - Aesthetic-aware Recommender System for Online Fashion Products. - DAFD: Domain Adaptation Framework for Fake News Detection. - Document Image Classification Method based on Graph Convolutional Network. - Continual Learning of 3D Point Cloud Generators. - Attention-Based 3D ResNet for Detection of Alzheimer's Disease Process. - Generation of a Large-Scale Line Image Dataset with Ground Truth Texts from Page-Level Autograph Documents. - DAP-BERT: Differentiable Architecture Pruning of BERT. - Trash Detection On Water Channels. - Tri-Transformer Hawkes Process: Three Heads are better than one. - PhenoDeep: A deep Learning-based approach for detecting reproductive organs from digitized herbarium specimen images. - Document-level Event Factuality Identification using Negation and Speculation Scope. - Dynamic Network Embedding by Time-Relaxed Temporal Random Walk. - Dual-band Maritime Ship Classification based on Multi-layer Convolutional Features and Bayesian Decision. - Context-Based Anomaly Detection via Spatial Attributed Graphs in Human Monitoring. - Domain-Adaptation Person Re-Identification via Style Translation and Clustering. - Multimodal Named Entity Recognition Via Co-attention-based Method with Dynamic Visual Concept Expansion. - Ego Networks. - Cross-modal based Person Re-Identification via Channel Exchange and adversarial Learning. - SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs. - Deep Neuroevolution: Training Neural Networks using a Matrix-free Evolution Strategy. - Weighted P-Rank: A Weighted Article Ranking Algorithm Based on a Heterogeneous Scholarly Network. - Clustering Friendly Dictionary Learning. - Understanding Test-Time Augmentation. - SphereCF: Sphere Embedding for Collaborative Filtering. - Concordant Contrastive Learning for Semi-supervised Node Classification on Graph. - Improving Shallow Neural Networks via Local and Global Normalization. - Underwater Acoustic Target Recognition with Fusion Feature. - Evaluating Data Characterization Measures for Clustering Problems in Meta-learning. - ShallowNet: An Efficient Lightweight Text Detection Network Based on Instance Count-aware Supervision Information. - Image Periodization for Convolutional NeuralNetworks. - BCN-GCN: A Novel Brain Connectivity Network Classification Method via Graph Convolution Neural Network for Alzheimer's Disease. - Triplet Mapping for Continuously Knowledge Distillation. - A Prediction-Augmented AutoEncoder for Multivariate Time Series Anomaly Detection.