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

Regular Papers.- A Dual-Branch Model for Color Constancy.- A
Multi-Aspect Multi-Granularity Pronunciation Assessment Method Based on
Branchformer Encoder and Hierarchical Aggregation.- A Multi-Expert
Collaborative Framework for Multimodal Named Entity Recognition.- A Novel
Human Abnormal Posture Detection Method Based on Spatial-Topological Feature
Fusion of Skeleton.- AD2AT: Audio Description to Alternative Text, a Dataset
of Alternative Text from Movies.- AMFT-YOLO: A Adaptive Multi-Scale YOLO
Algorithm with Multi-Level Feature Fusion for Object Detection in UAV
Scenes.- AMPLE: Emotion-Aware Multimodal Fusion Prompt Learning for Fake News
Detection.- An Analytical Method for Rendering Plenoptic Cameras 2.0 on 3D
Multi-Layer Displays.- Balancing Efficiency and Accuracy: An Analysis of
Sampling for Video Copy Detection.- BiCA-YOLO: Bidirectional Feature
Enhancement and Cross Coordinate Attention for Small Object Detection.- BLCC:
A Benchmark for Multi-LiDAR and Multi-Camera Calibration.-Boosting Human Pose
Estimation via Heatmap Refinement.- Camouflaged Object Detection Based on
Localization Guidance and Multi-Scale Refinement.- Chain of Thought Guided
Few-shot Fine-tuning of LLMs for Multimodal Aspect-based Sentiment
Classification.- CLIP Multi-modal Hashing for Multimedia
Retrieval.- Comparative Analysis of Relevance Feedback Techniques for Image
Retrieval.- Cross-View Geo-Localization via Learning Correspondence Semantic
Similarity Knowledge.- DART: Depth-Enhanced Accurate and Real-Time Background
Matting. Data-free Functional Projection of Large Language Models onto Social
Media Tagging Domain.- Deep Dual Internal Learning for Hyperspectral Image
Super-Resolution.- Detoxification of Unlabeled Dataset: Reducing Implicit
Class Imbalance Using Pseudo-Jacobian of GAN's Generator.- DistillSleep:
Leverage Self-Distillation to Improve Performance After Representation
Learning for Sleep Staging.- DocMamba: Robust Document Image Dewarping via
Selective State Space Sequence Modeling.- Dual-Task Feedback Learning for
Tongue Detection via Super-Resolution Integration.- Dynamic Exploration
Graph: A Novel Approach for Efficient Nearest Neighbor Search in Evolving
Multimedia Datasets.- EIA: Edge-aware Imperceptible Adversarial Attacks on 3D
Point Clouds.- Enhancing Environmental Monitoring through Multispectral
Imaging: The WasteMS Dataset for Semantic Segmentation of Lakeside
Waste.- ESC-MISR: Enhancing Spatial Correlations for Multi-Image
Super-Resolution in Remote Sensing.- Flat Local Minima for Continual learning
on Semantic Segmentation.- FoodMLLM-JP: Leveraging Multimodal Large Language
Models for Japanese Recipe Generation.- Frequency-aware Convolution for Sound
Event Detection.- Frequency-Based Unsupervised Low-Light Image Enhancement
Framework.- GFA-UDIS: Global-to-Flow Alignment for Unsupervised Deep Image
Stitching.