E-grāmata: PRICAI 2024: Trends in Artificial Intelligence: 21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024, Kyoto, Japan, November 18-24, 2024, Proceedings, Part III

.- Large Language Models.

.- MLRQA: A Dataset with Multimodal Logical Reasoning Challenges.

.- Fame Bias Large Language Models Change Their Judgement Depending on
Personal Name.

.- Distributed Population-based Simultaneous Perturbation Stochastic
Approximation for Fine-Tuning Large Language Models.

.- Transformer-Mamba-based Trident-Branch RGB-T Tracker.

.- MMAT: Multi-scale Multi-Attention Transformer for Fine-grained Wild Fungi
Visual Classification.

.- Enhancing Parameter-Efficient Transformers with Contrastive Syntax and
Regularized .- Dropout for Neural Machine Translation.

.- Computer Vision.

.- DB-FSCIL: Few-Shot Class-Incremental Learning Using Dual Bridges.

.- GMMotion: Neighborhood Information Matters for Online Multi-Pedestrian
Tracking.

.- Predicting Plain Text Imageability for Faithful Prompt-Conditional Image
Generation.

.- BFNet: A Bi-Frequency Fusion Semantic Segmentation Network for
High-Resolution Remote Sensing Images.

.- An improved model of detecting ground military targets from horizontal
view.

.- A Copy-Paste Data Augmentation Method For Urban Tree Detection.

.- A Novel Geometric-Encoded and Feature-Fused Model for Pressure
Distribution Prediction on Airfoils.

.- Artificial Intelligence-Guided Fully-Automatic Renal Segmentation.

.- Integrating Vision-Tool to Enhance Visual-Question-Answering in Special
Domains.

.- AGLTN: Attention-Based Global-Local Transformer Network for Ultra-High
Resolution Images.

.- GAMF-Net: A Lightweight Network for Semantic Segmentation of Land Cover
Recognition in Open-Pit Coal Mining Areas.

.- Action Recognition Based on Multi-Perspective Feature Excitation.

.- HQPAFT: Enhancing Low-Light Images with High-Quality Priors and Advanced
Feature  Transformations Using Only Normal Light Images.

.- A Reversible Data Hiding in Encryption Domain for JPEG Image Based on
Controllable  Ciphertext Range of Paillier Homomorphic Encryption Algorithm.

.- BEVTemp: Enhancing Vision-based Roadside 3D Object Detection with Temporal
Information.

.- CPNet: Controllable Point Cloud Generation Network Using Part-Level
Information.

.- AffViT: Fast Affine Medical Image Registration with Convolutional Vision
Transformer.

.- An Instance and Cloud Masks Guided Multi-source Fusion Network for Remote
Sensing Object Detection.

.- Image Gradient-Aided Photometric Stereo Network.

.- Enhancing Object Detection Accuracy with Hybrid Supervision and
Trans-stage Interaction.

.- Adaptive Threshold-Driven Semi-Supervised Facial Expression Recognition.

.- 3D-HRFC: 3D-Aware Image Generation at High Resolution with Faster
Convergence.

.- AF-SSD:Self-Attention Fusion Sampling and Fuzzy Classification for
Enhanced Small Object Detection.

.- A Facial Expression Recognition Model Based on a Hybrid Attention
Mechanism with . Multiple Information Spaces and Channels.

.- A Meta-Learning Method for Generalizable Face Forgery Detection.

.- Data-Free Quantization of Vision Transformers through Perturbation Aware
Image Synthesis.

.- HMM-VMamba: High-order Morphological Method Vision Mamba for Medical Image
Segmentation.

.- Evaluating Subtle PositiveNegative Facial Expression Transitions for
Monitoring Changes in Personal Internal States.

.- Image Generation Method for Addressing Class Imbalance in Small-Sample
Pulsar Candidates.

.- Efficient Matrix-Based Multi-View Projection Features Combined for
Multi-Modal 3D Semantic Segmentation.

.- Enhancing Multimodal Rumor Detection with Statistical Image Features and
Modal  Alignment via Contrastive Learning.

.- Audio-Driven Face Photo-Sketch Video Generation.

.- A Decoupling Video Frame Selection Method for Action Recognition.