Machine/deep learning methodologies for multimedia

INDUCTIVE RELATION PREDICTION FROM RELATIONAL PATHS AND CONTEXT WITH HIERARCHICAL TRANSFORMERS

A Multi-signal Perception Network For Textile Composition Identification

Dual-Path Cross-Modal Attention for better Audio-Visual Speech Extraction

Single-branch Network for Multimodal Training

Multimodal Propaganda Detection via Anti-persuasion Prompt Enhanced Contrastive Learning

CNN Filter for Super-Resolution with RPR functionality in VVC

SPARSE CONVOLUTION BASED OCTREE FEATURE PROPAGATION FOR LIDAR POINT CLOUD COMPRESSION

Unrestricted Anchor Graph based GCN for Incomplete Multi-view Clustering

A Mutli-stage Hierarchical Relational Graph Neural Network for Multimodal Sentiment Analysis

FedVMR: A New Federated Learning method for Video Moment Retrieval