Full Description
This two-volume set LNCS 14233-14234 constitutes the refereed proceedings of the 22nd International Conference on Image Analysis and Processing, ICIAP 2023, held in Udine, Italy, during September 11-15, 2023.The 85 full papers presented together with 7 short papers were carefully reviewed and selected from 144 submissions. The conference focuses on video analysis and understanding; pattern recognition and machine learning; deep learning; multi-view geometry and 3D computer vision; image analysis, detection and recognition; multimedia; biomedical and assistive technology; digital forensics and biometrics; image processing for cultural heritage; and robot vision.
Contents
Buffer-MIL: Robust Multi-instance Learning with a Buffer-based Approach.- Quasi-Online Detection of Take and Release Actions from Egocentric Videos.- Hashing for Structure-based Anomaly Detection.- Augmentation based on artificial occlusions for resilient instance segmentation.- Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations.- VM-NeRF: Tackling Sparsity in NeRF with View Morphing.- MOVING: a MOdular and flexible platform for embodied VIsual NaviGation.- Evaluation of 3D reconstruction pipelines under varying imaging conditions.- CarPatch: A Synthetic Benchmark for Radiance Field Evaluation on Vehicle Components.- Obstacle Avoidance and Interaction in Extended Reality: An Approach based on 3D Object Detection.- HMPD: a novel dataset for microplastics classification with digital holography.- Early detection of hip periprosthetic joint infections through CNN on Computed Tomography images.- Many-to-Many metrics: a new approach to evaluate the performance of structural damage detection networks.- Deepfakes Audio Detection leveraging audio spectrogram and Convolutional Neural Networks.- A deep Natural Language Inference predictor without language-specific training data.- Time-aware Circulant Matrices for Question-based Temporal Localization.- Enhancing Open-Vocabulary Semantic Segmentation with Prototype Retrieval.- Lightweight Blur Kernel Estimation Network for Blind Image Super-Resolution.- Hierarchical Pretrained Backbone Vision Transformer for Image Classification in Histopathology.- On using rPPG signals for DeepFake detection: a cautionary note.- An unsupervised learning approach to resolve phenotype to genotype mapping in budding yeasts vacuoles.- Food image classification: the benefit of in-domain transfer learning.- LCMV: Lightweight Classification Module for Video Domain Adaptation.- FEAD-D: Facial Expression Analysis in Deepfake Detection.- Large Class Separation is not what you need for Relational Reasoning-based OOD Detection.- BLUES: Before-reLU-EStimates Bayesian Inference for Crowd Counting.- Two is Better than One: Achieving High-Quality 3D Scene Modeling with a NeRF Ensemble.- BHAC-MRI: Backdoor & Hybrid Attacks on MRI Brain Tumor Classification Using CNN.- Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis.- Extrinsic Calibration of Multiple Depth Cameras for 3D Face Reconstruction.- A Deep Learning based Approach for Synthesizing Realistic Depth Maps.- Specialise to Generalise: the Person Re-identification Case.- Enhancing Hierarchical Vector Quantized Autoencoders for Image Synthesis through Multiple Decoders.- Dynamic Local Filters in Graph Convolutional Neural Networks.- An AI-Driven Prototype for Groundwater Level Prediction: Exploring the Gorgovivo Spring Case Study.- DiffDefense: Defending against Adversarial Attacks via Diffusion Models.- Exploring Audio Compression as Image Completion in Time-Frequency Domain.- Fuzzy Logic Visual Network (FLVN): A neuro-symbolic approach for visual features matching.- CISPc: Embedding images and point clouds in a joint concept space by contrastive learning.- Budget-Aware Pruning for Multi-Domain Learning.- Sparse Double Descent in Vision Transformers: real or phantom threat?.- Video Sonification to Support Visually Impaired People: the VISaVIS approach.- Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training.- The Specchieri MarVen Dataset: an Abbreviation-rich Dataset in Venetian Idiom.- Compensation for Patient Movements in CBCT Imaging for Dental Applications.- Spatial Exploration Indicators in the Remote Assessment of Visual Neglect.
