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 810, 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.

Inhalt

Regular Papers.- Modeling High-order Relationships between Human and Video for Emotion Recognition.- MPPQNet: A Moment-Preserving Product Quantization Neural Network for Progressive 3D Point Cloud Transmission.- MS-SAM:Multi-Scale SAM based on Dynamic Weighted Agent Attention.- MSA-Former: Multi-Scale Adaptive Transformer for Image Snow Removal.- MSD-YOLO : An Efficient Algorithm for Small Target Detection.- Multi-Modal Information Multi-Angle Mining For Multimedia Recommendation.-Multimodal Prompt Learning for Audio Visual Scene-aware Dialog.- Music2MIDI: Pop Music to MIDI Piano Cover Generation.- Noise-robust Separating Multi-source Aliased Vibration Signal Based on Transformer Demucs.- One-Shot Generative Domain Adaptation by Constructing Self-Amplifying Datasets.- Open-vocabulary Scene Graph Generation via Synonym-based Predicate Descriptor.- Operatic Singing Voice Synthesis From Inexperienced Voice Considering Tempo and Vowel Change.- Optimally Planning Drone Trajectories to Capture 3D Gaussian Splatting Objects.- PA2Net: Pyramid Attention Aggregation Network for Saliency Detection.- PianoPal: A Robotic Multimedia System for Interactive Piano Instruction Based on Q-learning and Real-time Feedback.- Poseidon: A NAS-Based Ensemble Defense Method against Multiple Perturbations.- Progressive Neural Architecture Generation with Weaker Predictors.- Pubic Symphysis-Fetal Head Segmentation Network Using BiFormer Attention Mechanism and Multipath Dilated Convolution.- QRALadder: QoE and Resource Consumption-Aware Encoding Ladder Optimization for Live Video Streaming.- Quantized-ViT Efficient Training via Fisher Matrix Regularization.- Real-Time Action Detection in Volleyball Matches Using DETR Architecture.- Revisit Data Association in Semantic SLAM Systems for Autonomous Parking.-RobSparse: Automatic Search for GPU-Friendly Robust and Sparse Vision Transformers.- Robust Active Speaker Detection in Challenging Environments Using GNN-Fused Multi-Modal Cues and Body Language.- RoLD: Robot Latent Diffusion for Multi-task Policy Modeling.- Rotation Methods for 360-degree Videos in Virtual Reality - A Comparative Study.- Saliency Based Data Augmentation for Few-shot Video Action Recognition.- Saliency Guided Optimization Of Diffusion Latents.- SCANet: Semantic Coherence Attention Network for Clothing Change Person Re-identification.- SCLSTE: Semi-Supervised Contrastive Learning-Guided Scene Text Editing.- Select and Order: Enhancing Few-Shot Image Classification through In-Context Learning.- Self-Supervised Reference-based Image Super-Resolution with Conditional Diffusion Model.