Read more
The sixteen-volume set, CCIS 2282-2297, constitutes the refereed proceedings of the 31st International Conference on Neural Information Processing, ICONIP 2024, held in Auckland, New Zealand, in December 2024.
The 472 regular papers presented in this proceedings set were carefully reviewed and selected from 1301 submissions. These papers primarily focus on the following areas: Theory and algorithms; Cognitive neurosciences; Human-centered computing; and Applications.
List of contents
Optimisation of Fibre Selection For Tubes Production in Manufacturing of Optic Cables.- Cross-Domain Evaluation of CNN-based and Generative Adversarial Networks Models Generalisability for (D)DoS Attack Detection in CPS and IoT.- Robust Design of Echo State Networks for Soft Sensor Applications
Based on Risk-Aware Optimization and Stability Testing.- Logic Error Localization in Student Programming Assignments Using Pseudocode and Graph Neural Networks.- FISHER: An Efficient Sim2sim Training Framework Dedicated in Multi-AUV Target Tracking via Learning from Demonstrations.- Revisiting Cross-Domain Problem for LiDAR-based 3D Object Detection.- Self-Supervised Pretraining-Enhanced Intelligent Quality Control for Ocean Observations with Limited Historical Data.- SHAPE: Smart Shaping with Adaptation Physically Excited Networks.- Accelerating Attentional Generative Adversarial Networks with Sampling Blocks.- Weak Supervision Techniques towards Enhanced ASR Models in Industry-level CRM Systems.- Guided Safe Diffusion: Prohibiting Diffusion Models from Generating Inappropriate Content.- A Fine-Tuned Multi-Classifier Optimization Framework towards Safety-Critical Classes.- Behavior-Driven Data Augmentation for Non-Intrusive Load Monitoring.- Data-Driven Approach to assess and identify gaps in healthcare set up in South Asia.- A Robust Tensor Decomposition Model for Traffic Data Imputation with Capped Frobenius Norm in Smart City.- A Federated Domain Generalization Method by Enhancing Knowledge Distillation With Stylistic Feature Dispatcher.- RetailEye: Supervised Contrastive Learning with Compliance Matching
for Retail Shelf Monitoring.- Solving Expensive Dynamic Multi-Objective Problem via Cross-Problem Knowledge Transfer.- XImgCom: Fine-tuned Text-Guided X-ray Image Synthesis for Airport Logistics Based on Hypercomplex Attention.- Multiclass semantic segmentation of satellite Imagery using
convolutional neural networks.- PPDA: A Privacy Preserving Framework for Distributed Graph Learning.- MonoTCM: Semantic-Depth Fusion Transformer for Monocular 3D Object Detection with Token Clustering and Merging.- Illumination Estimation and Fourier-Guided Component Prediction for
Enhancing Low-Light Images.- Efficient Visual Object Tracking with Temporal Context-Aware Token
Learning and Scale Adaptive Token Pruning.- Towards Unveiling the Potential of Fuzzy Values as Features: A Comparative Study in Cybercrime Text Analysis.- Hybrid Niching Differential Evolution with Restart Strategy for Multimodal Optimization.- StreetSyn: A Full Radiance Field Solution for Street and Vehicle Free-View Synthesis.
Summary
The sixteen-volume set, CCIS 2282-2297, constitutes the refereed proceedings of the 31st International Conference on Neural Information Processing, ICONIP 2024, held in Auckland, New Zealand, in December 2024.
The 472 regular papers presented in this proceedings set were carefully reviewed and selected from 1301 submissions. These papers primarily focus on the following areas: Theory and algorithms; Cognitive neurosciences; Human-centered computing; and Applications.
