E-grāmata: MultiMedia Modeling: 31st International Conference on Multimedia Modeling, MMM 2025, Nara, Japan, January 8-10, 2025, Proceedings, Part II

Regular Papers.- gFlow: Distributed Real-Time Reverse Remote Rendering
System Model.- Grounding Deliberate Reasoning in Multimodal Large Language
Models.- GWUNet: A UNet with Gated Attention and Improved Wavelet Transform
for Thyroid Nodules Segmentation.- HCV: Lightweight Hybrid CNN-Vision
Transformer for Visual Object Tracking.-HierArtEx: Hierarchical
Representations and Art Experts Supporting the Retrieval of Museums in the
Metaverse.- Hybrid Scalable Video Coding with Neural Compression and
Enhancement for Streaming Media.- Hyper-NeuS:Hypernetworks for Neural SDF
Implicit Surface Reconstruction by Volume Rendering.- Image-Generation AI
Model Retrieval by Contrastive Learning-based Style Distance
Calculation.- Improving Singing Voice Transcription Generalization with AI
Generated Accompaniments.- Infrared Small Target Detection with Feature
Refinement and Context Enhancement.- Innovative Lifelog Visualization and
Exploration in Virtual Reality - A Comparative Study.- Integrating S1&S2
Framework for Enhanced Semantic Match in Person
Re-identification.- Intra-Class Compact Facial Expression Recognition Based
on Amplitude Phase Separation.- Joint Decision Network with Modality-Specific
and Dual Interactive Features for Fake News Detection.- Kiite World:
Socializing Map-Based Music Exploration Through Playlist Sharing and
Synchronized Listening.- KuzushijiDiffuser: Japanese Kuzushiji Font
Generation with FontDiffuser.- LIESA: Low-light Image Enhancement with
Semantic Awareness.- Lightweight Dual Grouped Large-Kernel Convolutions for
Salient Object Detection Network.- Lightweight Motion-Aware Video
Super-Resolution for Compressed Videos.- LITA: LMM-guided Image-Text
Alignment for Art Assessment.- LLMs-based Augmentation for Domain Adaptation
in Long-tailed Food Datasets.- Making strides Security in Multimodal Fake
News Detection Models: A Comprehensive Analysis of Adversarial
Attacks.- MambaTalk: Speech-driven 3D Facial Animation with Mamba.- MC-YOLO:
Multi-scale Transmission Line Defect Target Recognition Network.- MDT-Net: A
Mask Decoder Tuning Strategy for CLIP-based Zero-shot 3D
Classification.- MICAN Multi-modal Inconsistency-based Cooperation Attention
Network for Fake News Detection.- MineTinyNet-YOLO: An Efficient Small Object
Detection Method for Complex Underground Coal Mine Scenarios.- Mix-YOLONet:
Deep Image Dehazing for Improving Object Detection.- MKSNet: Advanced Small
Object Detection in Remote Sensing Imagery with Multi-Kernel and Dual
Attention Mechanisms.- MLP-AMDC: A MLP Architecture for Adaptive-Mask-based
Dual-Camera Snapshot Hyperspectral Imaging.- MM-CARP: Multimodal Model with
Cross-modal Retrieval-Augmented and Visual Region Perception.-
Modality-Specific Hashing: Transform Cross-Modal Retrieval into Single-Modal
Retrieval.