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

Regular Papers.- SES-Net: Multi-dimensional Spot-Edge-Surface Network
for Nuclei Segmentation.- Skin-Adapter: Fine-Grained Skin-Color Preservation
for Text-to-Image Generation.- Small Tunes Transformer: Exploring Macro &
Micro-Level Hierarchies for Skeleton-Conditioned Melody
Generation.- SMG-Diff: Adversarial Attack Method Based on Semantic
Mask-Guided Diffusion.- SPLGAN-TTS:Learning Semantic and Prosody to Enhance
the Text-to-Speech Quality of Lightweight GAN Models.- SSCDUF:
Spatial-Spectral Correlation Transformer Based on Deep Unfolding Framework
for Hyperspectral Image Reconstruction.- SSDL: Sensor-to-Skeleton Diffusion
Model with Lipschitz Regularization for Human Activity
Recognition.- Structural Information-guided Fine-grained Texture Image
Inpainting.- Style Separation and Content Recovery for Generalizable Sketch
Re-identification and A New Benchmark.- Synchronization and Calibration of
Video Sequences acquired using Multiple Plenoptic 2.0
Cameras.- Target-Oriented Dynamic Denosing Curriculum Learning for Multimodel
Stance Detection.- TDM: Temporally-Consistent Diffusion Model for All-in-One
Real-World Video Restoration.- Temporal Closeness for Enhanced Cross-Modal
Retrieval of Sensor and Image Data.- The Right to an Explanation under the
GDPR and the AI Act.- Toward Appearance-based, Autonomous Landing Site
Identification for Multirotor Drones in Unstructured Environments.- Towards
Inclusive Education: Multimodal Classification of Textbook Images for
Accessibility.- Towards Visual Storytelling by Understanding Narrative
Context through Scene-Graphs.- TPS-YOLO: The Efficient Tiny Person Detection
Network Based on Improved YOLOv8 and Model Pruning.- Uncertainty-guided Joint
Semi-supervised Segmentation and Registration of Cardiac
Images.- Understanding the Roles of Visual Modality in Multimodal Dialogue:
An Empirical Study.- Vision-Language Pretraining for Variable-shot Image
Classification.- Visual Anomaly Detection on Topological Connectivity under
Improved YOLOv8.- Wavelet Integrated Convolutional Neural Network for ECG
Signal Denoising.- WavFusion: Towards wav2vec 2.0 Multimodal Speech Emotion
Recognition.- Zero-shot Sketch-based Image Retrieval with Hybrid Information
Fusion and Sample Relationship Modeling.- Special Session: ExpertSUM: Special
Session on Expert-Level Text Summarization from Fine-Grained Multimedia
Analytics.- CalorieVoL: Integrating Volumetric Context into Multimodal Large
Language Models for Image-based Calorie Estimation.- Can Masking Background
and Object Reduce Static Bias for Zero-shot Action Recognition?.- Special
Session: MLLMA: Special Session on Multimodal Large Language Models and
Applications.- Enhanced Anomaly Detection in 3D Motion through
Language-Inspired Occlusion-Aware Modeling.- Evaluating VQA Models'
Consistency in the Scientific Domain.- Image2Text2Image: A Novel Framework
for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image
Diffusion Models.- Quantifying Image-Adjective Associations by Leveraging
Large-Scale Pretrained Models.- TACST: Time-Aware Transformer for Robust
Speech Emotion Recognition.- TS-MEFM: A New Multimodal Speech Emotion
Recognition Network Based on Speech and Text Fusion.