MultiMedia Modeling 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29 – February 2, 2024, Proceedings, Part I

Where are Biases? Adversarial Debiasing with Spurious Feature Visualization.- Cross-Modal Hash Retrieval with Category Semantics.- Spatiotemporal Representation Enhanced ViT for Video Recognition.- SCFormer: A Vision Transformer with Split Channel in Sitting Posture Recognition.- Dive into Coarse-to-Fine Strategy in Single Image Deblurring.- TICondition: Expanding Control Capabilities for Text-to-Image Generation with Multi-Modal Conditions.- Enhancing Generative Generalized Zero Shot Learning via Multi-Space Constraints and Adapative Integration.- Joint Image Data Hiding and Rate-Distortion Optimization in Neural Compressed Latent Representations.- GSUNet: A Brain Tumor Segmentation Method Based On 3D Ghost Shuffle U-Net.- ACT: Action-associated and Target-related Representations for Object Navigation.- Foreground Feature Enhancement and Peak & Background Suppression for Fine-Grained Visual Classification.- YOLOv5-SRR: Enhancing YOLOv5 for Effective Underwater Target Detection.- Image Clustering and Generation with HDGMVAE-I.- “Car or Bus?" CLearSeg: CLIP-enhanced Discrimination among Resembling Classes for Few-Shot Semantic Segmentation.- PANDA: Prompt-based Context- and Indoor-aware Pretraining for Vision and Language Navigation.- Cross-Modal Semantic Alignment Learning for Text-based Person Search.- Point Cloud Classification via Learnable Memory Bank.- Adversarially Regularized Low-Light Image Enhancement.- Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptation.- PMGCN:Preserving measuring mapping prototype graph calibration network for few-shot learning.- ARE-CAM: An interpretable approach to quantitatively evaluating the adversarial robustness of deep models based on CAM.- SSK-Yolo:Global feature-driven small object detection network for images.- MetaVSR: A Novel Approach to Video Super-Resolution for Arbitrary Magnification.- From Skulls to Faces: A Deep Generative Framework for Realistic 3D Craniofacial Reconstruction.- Structure-aware Adaptive Hybrid Interaction Modeling for Image-Text Matching.- Using Saliency and Cropping to Improve Video Memorability.- Contextual Augmentation with Bias Adaptive for Few-shot Video