MultiMedia Modeling

Self-distillation Enhanced Vertical Wavelet Spatial Attention for Person Re-identification.- High Capacity Reversible Data Hiding in Encrypted Images Based onPixel Value Preprocessing and Block Classification.- HPattack: An Effective Adversarial Attack for Human Parsing.- Dynamic-Static Graph Convolutional Network for Video-Based Facial Expression Recognition.- Hierarchical Supervised Contrastive Learning for Multimodal Sentiment Analysis.- Semantic Importance-Based Deep Image Compression Using A Generative Approach.- Drive-CLIP: Cross-modal Contrastive Safety-Critical Driving Scenario Representation Learning and Zero-shot Driving Risk Analysis.- MRHF: Multi-stage Retrieval and Hierarchical Fusion for Textbook Question Answering.- Multi-scale Decomposition Dehazing with Polarimetric Vision.- CLF-Net: A Few-shot Cross-Language Font Generation Method.- Multi-dimensional Fusion and Consistency for Semi-supervised Medical Image Segmentation.- Audio-Visual Segmentation By Leveraging Multi-Scaled Features Learning.- Multi-head Hashing with Orthogonal Decomposition for Cross-modal Retrieval.- Fusion Boundary and Gradient Enhancement Network for Camouflage Object Detection.- Find the Cliffhanger: Multi-Modal Trailerness in Soap Operas.- SM-GAN: Single-stage and Multi-object Text Guided Image Editing.- MAVAR-SE: Multi-scale Audio-Visual Association Representation Network for End-to-end Speaker Extraction.- NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide Images.- Improving Small License Plate Detection with Bidirectional Vehicle-plate Relation.- A Purified Stacking Ensemble Framework for Cytology Classification.- SEAS-Net: Segment Exchange Augmentation for Semi-Supervised Brain Tumor Segmentation.- Super-Resolution-Assisted Feature Refined Extraction for Small Objects in Remote Sensing Images.- Lightweight Image Captioning Model Based on Knowledge Distillation.- Irregular License Plate Recognition via Global Information Integration.- TNT-Net: Point Cloud Completion by Transformer in Transformer.- Fourier Transformer for Joint Super-Resolution and Reconstruction ofMr Image.- MVD-NeRF: Resolving Shape-Radiance Ambiguity via Mitigating View Dependency.- DPM-Det: Diffusion Model Object Detection Based on DPM-Solver++Guided Sampling.- CT-MVSNet: Efficient Multi-View Stereo with Cross-scale Transformer.- A Coarse and Fine Grained Masking Approach for Video-groundedDialogue.- Deep self-supervised subspace clustering with triple loss.- LigCDnet:Remote Sensing Image Cloud Detection Based on Lightweight Framework.- Gait Recognition Based on Temporal Gait Information Enhancing.- Learning Complementary Instance Representation with Parallel Adaptive Graph-Based Network for Action Detection.- CESegNet:Context-Enhancement Semantic Segmentation NetworkBased on Transformer.- MoCap-Video Data Retrieval with Deep Cross-Modal Learning.- LRATNet: Local-Relationship-Aware Transformer Network for TableStructure Recognition.