MultiMedia Modeling

This five-volume set LNCS 15520-15524 constitutes the proceedings of the 31st International Conference on Multimedia Modeling, MMM 2025, held in Nara, Japan, January 8-10, 2025.

The 135 full papers and 41 short papers presented in these proceedings were carefully reviewed and selected from 348 submissions. The MMM conference was organized in topics related to multimedia modelling, particularly: audio, image, video processing, coding and compression; multimodal analysis for retrieval applications, and multimedia fusion methods.

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.