El. knyga: MultiMedia Modeling: 31st International Conference on Multimedia Modeling, MMM 2025, Nara, Japan, January 8-10, 2025, Proceedings, Part III

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.