El. knyga: MultiMedia Modeling: 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29 - February 2, 2024, Proceedings, Part III

Global-to-Local Feature Mining Network for RGB-Infrared
Person Re-Identification.- Semantic Transition Detection for Self-Supervised
Vide Scene Segmentation.- Multi-Task Collaborative Network for Image-text
Retrieval.- FGENet:Fine-Grained Extraction Network for Congested Crowd
Counting.- MSMV-UNet : A 2.5D Stroke Lesion Segmentation Method based
on Multi-slice Feature Fusion.- Non-Local Spatial-Wise and Global
Channel-Wise Transformer forEfficient Image
Super-Resolution.- MobileViT-FocR: MobileViT with Fixed-One-Centre Loss and
Gradient Reversal for Generalised Fake Face Detection.- ASF-Conformer: Audio
Scoring Conformer with FFC for Speaker Verification in Noisy
Environments.- Prior-Knowledge-Free Video Frame Interpolation with
Bidirectional Regularized Implicit Neural Representations.- Two-Stage
Reasoning Network with Modality Decomposition for TextVQA.- Localization and
Local Motion Magnification of Pulsatile Regions in Endoscopic Surgery
Videos.- Co-speech Gesture Generation with Variational Auto
Encoder.- Differentiable Neural Architecture Search Based on
Efficient Architecture for Lightweight Image Super-Resolution.- Learning
Collaborative Reinforcement Attention for 3D Face Reconstruction and Dense
Alignment.- Exploring Multi-Modal Fusion for Image Manipulation Detection
and Localization.- Object-based Spatio-Temporal Heterogeneous Network for
VideoQA.- Adaptive Token Selection and Fusion Network for
Multimodal Sentiment Analysis.- Exploring Imperceptible Adversarial Examples
in YCbCr Color Space.- Fractional-order image moments and
applications.- Time-Quality Tradeoff of MuseHash Query Processing
Performance.- Dual-Fisheye Image Stitching via Unsupervised Deep
Learning.- CA-GAN: Conditional Adaptive Generative Adversarial Network
for Text-to-Image Synthesis.- RDC-YOLOv5:Improved Safety Helmet Detection in
Adverse Weather.- Sustainable Commercial Fishery Control using Multimedia
Forensics Data from Non-trusted, Mobile Edge Nodes.- MC-TCMNER: A Multi-Modal
Fusion Model Combining Contrast Learning Method for Traditional Chinese
Medicine NER.- C3-PO: A Convolutional Neural Network for COVID Onset
Predictionfrom Cough Sounds.- Pseudo-label based Unsupervised Momentum
Representation Learning for Multi-domain Image Retrieval.- DFGait:
Decomposition Fusion Representation Learning for Multimodal Gait
Recognition.-  MoPE: Mixture of Pooling Experts Framework for Image-Text
Retrieval.- Multi-Modal Video Topic Segmentation with Dual-Contrastive
Domain Adaptation.- Unsupervised Multi-Collaborative Learning Network for 3D
Face Reconstruction.- A Region Based Non-overlapping Reference Speech
Estimation Method for Speaker Extraction.- Self-Supervised Edge Structure
Learning forMulti-View Stereo and Parallel Optimization.- Prototype-Enhanced
Hypergraph Learning for Heterogeneous Information Networks.- A Language-based
solution to enable Metaverse Retrieval.- Part-aware Prompt Tuning For Weakly
Supervised Referring Expression Grounding.- Adversarially Robust Deepfake
Detection via Adversarial Feature Similarity Learning.- A Multidimensional
Taxonomy Model for Music Tangible User Interfaces.