Neural Information Processing 31st International Conference, ICONIP 2024, Auckland, New Zealand, December 2–6, 2024, Proceedings, Part IX

The eleven-volume set LNCS 15286-15295 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.

Frequency-Constraint VQ-VAE for Adaptive MRI Segmentation.- Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer Importance Resides In Activations: Fast Input-Based Nonlinearity Pruning.- Open-Vocabulary Self-Interactive Semantic Segmentation.- Fine-Grained Transformer Encoder of Image-Text Retrieval for Streaming Data in Cross-Modal Continual Learning.- Generative AuDio Watermarking Technique (ADWT): robust identification for meaningful regulatory intervention.- CMGH:Label Co-occurrence-Enhanced Contrastive Multi-Granularity Hashing Cross-Modal Retrieval Optimizing Passage Retrieval with Dual-Directional Similarity Propagation.- Text2SPARQL: Grammar Pre-training for Text-to-QDMR Semantic Parsers from Intermediate Question Decompositions.- AMMCR: Adaptive Multi-view Multi-behavior Contrastive Learning Recommendation.- LGCMNet: Multimodal Sentiment Analysis Network Based on Language-Guided Cross-Modal Interaction.- Multi-modal Knowledge Graph Link Prediction via Neural Optimal Transport.- Cross modal Memory Attention Network with Multi-view for Multi-modal Rumor Detection.- NCSV: A Multimodal Benchmark for Negative Chinese Short Video Detection with Social Context Highlight Detection in Podcasts: A Multimodal Deep Learning Approach.- Wongsapat Phuengpanyaloet, Nonpipat Boonruengkhao, Viktor Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales.- T-EPTNet: Multi-Task Acoustic Scene Classification with Efficient Parameter Tuning.- Multi-modal Scene Global Fusion Framework for Enhanced Depth Estimation.- AIM-MIL: Adversarial Instance Mining for Robust Multi-Instance Learning in Whole Slide Image Classification.- Asymmetric Language-Aware Feature Learning for Low-Resource Cross-lingual Image Caption.- Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models.- Optimizing Learnable Frequency-domain Filterbanks for Depression Detection via Speech Representation Disentanglement.- A Novel Visual-Enhanced Dual Stream Long-Term Decision Framework for Large Language Model Agents.- Tailored Domain-specific Summaries: A Two-Stage Method Combining Extractive and Abstractive Summarization Models.- Related Work Generation with Variational Sequential Planning.- Enhanced Stance Detection using Cascaded Siamese Networks with Attention Mechanism.- BPDec: Unveiling the Potential of Masked Language Modeling Decoder in BERT Model Pretraining.- AttentionMix: A guided text data augmentation method relying on attention.- Integrating Narrow-Deep Local and Wide-Shallow Global Convolutional Model for Cloud Workload Prediction.- Boosting Self-Effcacy and Performance of Large Language Models via Verbal Effcacy Stimulations.- OneWORD: Adversarial Text Detection and Prediction Restoration Using One-Word Perturbation.- PVEIN: A Pretrained Vertex Embedding Infer Network for Open-domain Question Answer Scoring.