Neural Information Processing: 31st International Conference, ICONIP 2024, Auckland, New Zealand, December 26, 2024, Proceedings, Part VIII [Paperback]

The eleven-volume set LNCS 15286-15296 constitutes the refereed proceedings of the 31st International Conference on Neural Information Processing, ICONIP 2024, held in Auckland, New Zealand, in December 2024.The 318 regular papers presented in the proceedings set were carefully reviewed and selected from 1301 submissions. They focus on four main areas, namely: theory and algorithms; cognitive neurosciences; human-centered computing; and applications.

Generalized Multi-Scale Separable EPI Information for Light Field Image Super-Resolution.- ForgeryGPT: Cross-domain Face Forgery Detection using Large Vision-Language Models.- MFCA: Multimodal Object Detection based on Feature Calibration and Aggregation.- Omnidirectional Linear Attention Module for Penalty Shootout Video Understanding.- UOA-RCNN: detect anything with Unknown Object Aware RCNN.- WOODWIND: Few-shot Object Detector with Knowledge Distillation.- LITE: A Paradigm Shift in Multi-Object Tracking with Efficient ReID Feature Integration.- LSReGen: Large-Scale Regional Generator via Backward Guidance Framework.- AAFE-Net:Agent-Based Adaptive Feature Enhanced Network for Leather Defect Detection.- AA-RPN: Adaptive Anchor-based Region Proposal Network for Remote Sensing Object Detection.- Asterisk sparse convolutional networks for 3D object detection Shifted Window Fourier Transform And Retention For Image Captioning.- FOPS-V: Feature-Aware Optimization and Parallel Scale Fusion for 3D Human Reconstruction in Video.- PEBTrack: A Performance-Efficiency Balance Tracker for Aerial Scenario.- Multi-ScallÓ(