E-raamat: Image Analysis and Processing - ICIAP 2023: 22nd International Conference, ICIAP 2023, Udine, Italy, September 11-15, 2023, Proceedings, Part II

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.