Neural Information Processing: 30th International Conference, ICONIP 2023, Changsha, China, November 20–23, 2023, Proceedings, Part XII(1966 Communications in Computer and Information Science)

The nine-volume set constitutes the refereed proceedings of the 30th International Conference on Neural Information Processing, ICONIP 2023, held in Changsha, China, in November 2023.   The 1274 papers presented in the proceedings set were carefully reviewed and selected from 652 submissions.  The ICONIP conference aims to provide a leading international forum for researchers, scientists, and industry professionals who are working in neuroscience, neural networks, deep learning, and related fields to share their new ideas, progress, and achievements.

Table of Contents:
​Applications.- PBTR: Pre-training and Bidirectional Semantic Enhanced Trajectory Recovery.- Event-aware Document-level Event Extraction via Multi-granularity Event Encoder.- Curve Enhancement: A No-Reference Method for Low-light Image Enhancement.- A deep joint model of Multi-Scale intent-slots Interaction with Second-Order Gate for SLU.- Instance-aware and Semantic-guided Prompt for Few-shot Learning in Large Language Models.- Graph Attention Network Knowledge Graph Completion Model Based on Relational Aggregation.- SODet: A LiDAR-based Object Detector in Bird’s-Eye View.- Landmark-assisted Facial Action Unit Detection with Optimal Attention and Contrastive Learning.- Multi-Scale Local Region-Based Facial Action Unit Detection with Graph Convolutional Network.- CRE: An Efficient Ciphertext Retrieval Scheme based on Encoder.- Sentiment Analysis Based on Pre-trained Language Models: Recent Progress.- Improving Out-of-Distribution Detection with Margin-Based Prototype Learning.- Text-to-Image Synthesis With Threshold-Equipped Matching-Aware GAN.- Joint Regularization Knowledge Distillation.- Dual-Branch Contrastive Learning for Network Representation Learning.- Multi-Granularity Contrastive Siamese Networks for Abstractive Text Summarization.- Joint Entity and Relation Extraction for Legal Documents based on Table Filling.- Dynamic Knowledge Distillation for Reduced Easy Examples.- Fooling Downstream Classifiers via Attacking Contrastive Learning Pre-trained Models.- Feature Reconstruction Distillation with Self-attention.- DAGAN: Generative Adversarial Network with Dual Attentionenhanced GRU for Multivariate Time Series Imputation.- Knowledge-Distillation-Warm-Start Training Strategy for Lightweight Super-Resolution Networks.- SDBC: A Novel and Effective Self-Distillation Backdoor Cleansing Approach.- An Alignment and Matching Network with Hierarchical Visual Features for Multimodal Named Entity and Relation Extraction.- Multi-view Consistency View Synthesis.- A reinforcement learning-based controller designed for Intersection signal suffering from Information Attack.- Dual-Enhancement Model of Entity Pronouns and Evidence Sentence for Document-level Relation Extraction.- Nearest Memory Augmented Feature Reconstruction for Unified Anomaly Detection.- Deep Learning Based Personalized Stock Recommender System.- Feature-Fusion-Based Haze Recognition in Endoscopic Images.- Retinex Meets Transformer: Bridging Illumination and Reflectance Maps for Low-light Image Enhancement.- Make Spoken Document Readable: Leveraging Graph Attention Networks for Chinese Document-Level Spoken-to-Written Simplification.- MemFlowNet: A Network for Detecting Subtle Surface Anomalies with Memory Bank and Normalizing Flow.- LUT-LIC: Look-up Table-Assisted Learned Image Compression.- Oil and GasAutomatic Infrastructure Mapping: Leveraging HighResolution Satellite Imagery through fine-tuning of object detection models.- AttnOD: An Attention-based OD Prediction Model with Adaptive Graph Convolution.- CMMix: Cross-Modal Mix Augmentation between Images and Texts for Visual Grounding.- A Relation-oriented Approach for Complex Entity Relation Extraction.- A Revamped Sparse Index Tracker leveraging $K$–\,Sparsity and Reduced Portfolio Reshuffling.- Anomaly detection of fixed-wing unmanned aerial vehicle (UAV) based on cross-feature-attention LSTM network.- Spatial and Frequency Domains Inconsistency Learning for Face Forgery Detection.- Enhancing Camera Position Estimation by Multi-View Pure Rotation Recognition and Automated Annotation Learning.- Detecting Adversarial Examples Via Classification Difference of a Robust Surrogate Model.- Minimizing Distortion in Linguistic Steganography via Adaptive Language Model Tuning.- Efficient Chinese Relation Extraction with Multi-entity Dependency Tree Pruning and Path-Fusion.- A lightweight text classification model based on Label Embedding Attentive mechanism.