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.
Applications.- Improve Conversational Search with Multi-Document
Information.- Recurrent Update Representation Based on Multi-Head Attention
Mechanism for Joint Entity and Relation Extraction.- p Hashing for
Multi-label Image Retrieval with Similarity Matrix Optimization of Hash
Centers and Anchor Constraint of Center Pairs.- MDAM: Multi-Dimensional
Attention Module for Anomalous Sound Detection.- A Corpus of Quotation
Element Annotation for Chinese Novels: Construction, Extraction and
Application.- Decoupling Style from Contents for Positive Text Reframing.-
Multi-level Feature Enhancement Method For Medical Text Detection.- Neuron
Attribution-Based Attacks Fooling Object Detectors.- DKCS: A Dual
Knowledge-Enhanced Abstractive Cross-Lingual Summarization Method based on
Graph Attention Networks.- A Joint Identification Network for Legal Event
Detection.- YOLO-D: Dual-branch infrared distant target detection based on
multi-levelweighted feature fusion.- Graph Convolutional Network based
Feature Constraints Learning for Cross-Domain Adaptive Recommendation.- A
Hybrid Approach Using Convolution and Transformer for Mongolian Ancient
Documents Recognition.- Incomplete Multi-view Subspace Clustering Using
Non-Uniform Hyper-Graph for High-Order Information.- Deep Learning-Empowered
Unsupervised Maritime Anomaly Detection.- Hazardous Driving Scenario
Identification with Limited Training Samples.- Machine Unlearning with Affine
Hyperplane Shifting and Maintaining for Image Classification.- An
Interpretable Vulnerability Detection Method Based on Multi-task
Learning.- Co-GAN:A Text-to-Image Synthesis Model with Local and Integral
Features.- Graph Contrastive ATtention Network for Rumor
Detection.- E3-MG:End-to-End Expert Linking via Multi-Granularity
Representation Learning.- TransCenter: Transformer in Heatmap and A New Form
of Bounding Box.- Causal-Inspired Influence Maximization in Hypergraphs Under
Temporal Constraints.- Enhanced Generation of Human Mobility Trajectory with
Multiscale Model.- SRLI:Handling Irregular Time Series with a Novel
Self-supervised Model based on Contrastive Learning.- Multimodal Event
Classification in Social Media.- ADV-POST: Physically Realistic Adversarial
Poster for Attacking Semantic Segmentation Models in Autonomous
Driving.- Uformer++: Light Uformer for Image Restoration.- Can language
really understand depth?.- Remaining Useful Life Prediction of Control Moment
Gyro in Orbiting Spacecraft based on Variational Autoencoder.- Dynamic
Feature Distillation.- Detection of Anomalies and Explanation in
Cybersecurity.- Document-Level Relation Extraction with Relation Correlation
Enhancement.- Multi-scale Directed Graph Convolution Neural Network for Node
Classification Task.- Dual Knowledge Distillation for Neural Machine
Translation.- Probabilistic AutoRegressive Neural Networks for Accurate
Long-range Forecasting.- Stereoential Net: Deep Network for Learning Building
Height Using Stereo Imagery.- FEGI: A Fusion Extractive-Generative Model for
Dialogue Ellipsis and Coreference Integrated Resolution.- Assessing and
Enhancing LLMs: A Physics and History Dataset and One-More-Check Pipeline
Method.- Sub-Instruction and Local Map Relationship Enhanced Model for Vision
and Language Navigation.- TFormer: Cross-Level Feature Fusion in Object
Detection.- Improving Handwritten Mathematical Expression Recognition via an
Attention Refinement Network.- Dual-Domain Learning For JPEG Artifacts
Removal.- Graph-based Vehicle Keypoint Attention Model for Vehicle
Re-identification.- POI Recommendation based on Double-level Spatio-temporal
Relationship in Locations and Categories.- Multi-Feature Integration Neural
Network with Two-Stage Training for Short-Term Load Forecasting.
Lisainfo e-raamatute kohta