PRICAI 2024: Trends in Artificial Intelligence

The five-volume proceedings set LNAI 15281-15285, constitutes the refereed proceedings of the 21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024, held in Kyoto, Japan, in November 1824, 2024.

The 145 full papers and 35 short papers included in this book were carefully reviewed and selected from 543 submissions.

The papers are organized in the following topical sections:

Part I: Machine Learning, Deep Learning

Part II: Deep Learning, Federated Learning, Generative AI, Natural Language Processing, Large Language Models,

Part III: Large Language Models, Computer Vision

Part IV: Computer Vision, Autonomous Driving, Agents and Multiagent Systems, Knowledge Graphs, Speech Processing, Optimization

Part V: Optimization, General Applications, Medical Applications, Theoretical Foundations of AI

Klappentext

The five-volume proceedings set LNAI 15281-15285, constitutes the refereed proceedings of the 21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024, held in Kyoto, Japan, in November 18-24, 2024. The 145 full papers and 35 short papers included in this book were carefully reviewed and selected from 543 submissions. The papers are organized in the following topical sections: Part I: Machine Learning, Deep Learning Part II: Deep Learning, Federated Learning, Generative AI, Natural Language Processing, Large Language Models, Part III: Large Language Models, Computer Vision Part IV: Computer Vision, Autonomous Driving, Agents and Multiagent Systems, Knowledge Graphs, Speech Processing, Optimization Part V: Optimization, General Applications, Medical Applications, Theoretical Foundations of AI

Inhalt

.- Deep Learning.
.- STLB-GN: Spatio-Temporal Dual Graph Network with Learnable Bases.
.- Rethinking the Reliability of Post-hoc Calibration Methods under Subpopulation Shift.
.- Zero-shot Heterogeneous Graph Embedding via Semantic Extraction.
.- TG-PhyNN: An Enhanced Physically-Aware Graph Neural Network framework for forecasting Spatio-Temporal Data.
.- Stock Market Index Movement Prediction using Partial Contextual Embedding BERT-LSTM.
.- SCBC: A Supervised Single-cell Classification Method Based on Batch Correction for ATAC-seq Data.
.- TS-CATMA: A Lung Cancer Electronic Nose Data Classification Method Based on Adversarial Training and Multi-Scale Attention.
.- Visualizing the Unseen: Arabic Image-to-Story Generation Using Deep Learning Techniques.
.- Federated Learning.
.- Federated Prompt Tuning: When is it Necessary?.
.- Dirichlet-Based Local Inconsistency Query Strategy for Active Domain Adaptation.
.- FedSD: Cross-Heterogeneous Federated Learning Based on Self-Distillation.
.- Personalized Federated Learning with Feature Alignment via Knowledge Distillation.
.- Multi-Party Collaborative Hate Speech Study on Social Media via Personalized Federated Learning.
.- Preserving Individual User's Right to be Forgotten in Enterprise-Level Federated Learning.
.- Generative AI.
.- Dance Generation From Music with Enhanced Beat.
.- Contrastive Prototype Network for Generative Zero-Shot learning.
.- Steganography: An improved robust model for deep hidden network.
.- Human- and AI-Generated Marketing Content Comparison Corpus, Evaluation, and Detection.
.- Natural Language Processing.
.- Mongolian-Chinese Cross-lingual Topic Detection Based on Knowledge Distillation and Contrastive Learning Methods.
.- Emergence of Grounded Language Representations for Continuous Object Properties through Decentralized Embodied Learning.
.- AI-facilitation for consensus-building by virtual discussion using large language models.
.- False Positive Detection for Text-based Person Retrieval.
.- An End-to-End Method for Chinese Spelling Error Detection and Correction.
.- Dialogue Summarization based on Feature Extraction and Commonsense Injection.
.- SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq .- Personalized Generation with Causal Inference.
.- Document-Level Relation Extraction Model Based On Boundary Distance Loss And Long-Tail Relation Enhancement.
.- MCQG: Reading Comprehension Multiple Choice Questions Generation based on Pre-trained Language Models.
.- ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification.
.- EC-PEFT: An Expertise-Centric Parameter-Efficient Fine-Tuning Framework for Large Language Models.
.- Enhanced Classification of Delay Risk Sources in Road Construction Using Domain- Knowledge-Driven.
.- Modeling the Structural and Semantic Features for Japanese Lyrics Generation of J-pop Songs.
.- FINE-LMT: Fine-grained Feature Learning for Multi-Modal Machine Translation.
.- Segmentation Strategies and Data Enrichment for Improved Abstractive Summarization of Burmese Language.
.- Constrained Reasoning Chains for Enhancing Theory-of-Mind in Large Language Models.
.- Spatial-Temporal Union Channel Enhancement for Continuous Sign Language Recognition.
.- KLoB: a Benchmark for Assessing Knowledge Localization Methods in Language Models.
.- Cross-lingual Entity Alignment Model based on Multi-entity Enhancement and Semantic Information.
.- Large Language Models.
.- A Decomposed-Distilled Sequential Framework for Text-to-Table Task with LLMs.
.- Are Dense Retrieval Models Few-Shot Learners?.
.- An Empirical Study of Leveraging PLMs and LLMs for Long-Text Summarization.
.- A Novel MLLMs-based Two-stage Model for Zero-shot Multimodal Sentiment Analysis.
.- DeepTTS: Enhanced Transformer-Based Text Spotter via Deep Interaction Between Detection and Recognition Tasks.