Programme

Invited speakers

Oral session 1.A

Session Chair: Giovanni Maria Farinella

10:15 - 10:39

CarPatch: A Synthetic Benchmark for Radiance Field Evaluation on Vehicle Components

Di Nucci, Davide; Simoni, Alessandro; Tomei, Matteo; Ciuffreda, Luca; Vezzani, Roberto; Cucchiara, Rita

10:39 -11:03

Evaluation of 3D reconstruction pipelines under varying imaging conditions

Marelli, Davide; Bianco, Simone; Ciocca, Gianluigi

11:03 - 11:27

CISPc: Embedding images and point clouds in a joint concept space by contrastive learning

Sbrolli, Cristian; Cudrano, Paolo; Matteucci, Matteo

11:27 -11:51

Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation

Nocentini, Federico; Ferrari, Claudio; Berretti, Stefano

11:51 -12:15

VM-NeRF: Tackling Sparsity in NeRF with View Morphing

Bortolon, Matteo; Del Bue, Alessio; Poiesi, Fabio

Oral session 1.P

Session Chair: Primo Zingaretti

16:00 - 16:24 

Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis

Cocchi, Federico; Baraldi, Lorenzo; Poppi, Samuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita

16:24 - 16:48

A request for clarity over the End of Sequence token in the Self-Critical Sequence Training

Hu, Jia Cheng; Cavicchioli, Roberto; Capotondi, Alessandro

16:48 - 17:12

Food image classification: the benefit of in-domain transfer learning

Touijer, Larbi; Pastore, Vito Paolo; Odone, Francesca

17:12 - 17:36

BLUES: Before-reLU-EStimates Bayesian Inference for Crowd Counting

Ledda, Emanuele; Delussu, Rita; Putzu, Lorenzo; Fumera, Giorgio; Roli, Fabio

17:36 -18:00

Semi-supervised classification for Remote Sensing datasets

Hernandez-Sequeira, Itza A; Fernandez-Beltran, Ruben; Xu, Yonghao; Ghamisi, Pedram; Pla, Filiberto

18:00 - 18:24

Hashing for Structure-based Anomaly Detection

Leveni, Filippo; Magri, Luca; Alippi, Cesare; Boracchi, Giacomo

Oral session 2.A

Session Chair: Cosimo Distante

10:15 - 10:39

Early detection of hip periprosthetic joint infections through CNN on Computed Tomography images

Guarnera, Francesco; Rondinella, Alessia; Giudice, Oliver; Ortis, Alessandro; Battiato, Sebastiano; Rundo, Francesco; Fallica, Giorgio; Traina, Francesco; Conoci, Sabrina

10:39 -11:03

Sparse Double Descent in Vision Transformers: real or phantom threat?

Quetu, Victor; Milovanovic, Marta; Tartaglione, Enzo

11:03 - 11:27

Continual Source-Free Unsupervised Domain Adaptation

Ahmed, Waqar; Morerio, Pietro; Murino, Vittorio

11:27 -11:51

A differentiable entropy model for learned image compression

Presta, Alberto; Grangetto, Marco; Fiandrotti, Attilio; Tartaglione, Enzo

11:51 -12:15

A deep Natural Language Inference predictor without language-specific training data

Corradi, Lorenzo; Setti, Francesco; Del Bonifro, Francesca

Oral session 2.P

Session Chair: Vittorio Murino

16:00 - 16:24 

Large Class Separation is not what you need for Relational Reasoning-based OOD Detection

Lu, Lorenzo L; D'ascenzi, Giulia; Cappio Borlino, Francesco; Tommasi, Tatiana

16:24 - 16:48

Active Class Selection for Dataset Acquisition in Sign Language Recognition

Bicego, Manuele; Vazquez-Enriquez, Manuel; Alba-Castro, Jose

16:48 - 17:12

Towards facial expression robustness in multi-scale wild environments

Freire Obregon, David; Hernandez-Sosa, Daniel; Santana, Oliverio J.; Lorenzo-Navarro, Javier; Castrillón-Santana, Modesto

Oral session 3.A

Session Chair: Costantino Grana

10:15 - 10:39

SCENE-pathy: Capturing the Visual Selective Attention of People Towards Scene Elements

Toaiari, Andrea; Cunico, Federico; Taioli, Francesco; Caputo, Ariel; Menegaz, Gloria; Giachetti, Andrea; Farinella, Giovanni Maria; Cristani, Marco

10:39 -11:03

On using rPPG signals for DeepFake detection: a cautionary note

D'amelio, Alessandro; Lanzarotti, Raffaella; Patania, Sabrina; Grossi, Giuliano; Cuculo, Vittorio; Valota, Andrea; Boccignone, Giuseppe

11:03 - 11:27

Quasi-Online Detection of Take and Release Actions from Egocentric Videos

Scavo, Rosario; Ragusa, Francesco; Farinella, Giovanni Maria; Furnari, Antonino

11:27 -11:51

GCK-Maps: a scene unbiased representation for efficient Human Action Recognition

Nicora, Elena; Pastore, Vito Paolo; Noceti, Nicoletta

11:51 -12:15

Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations

Tur, Anil Osman; Dall'Asen, Nicola; Beyan, Cigdem; Ricci, Elisa

Poster session 1

14:00 – 16:00

An Effective CNN-Based Super Resolution Method for Video Coding

Peng, Shuang; Jiang, Dong; Lin, Jucai; Fang, Cheng; Yin, Jun

14:00 – 16:00

Enhancing Open-Vocabulary Semantic Segmentation with Prototype Retrieval

Barsellotti, Luca; Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita

14:00 – 16:00

Self-Similarity Block for Deep Image Denoising

Peretti, Edoardo; Stucchi, Diego; Carrera, Diego; Boracchi, Giacomo

14:00 – 16:00

Target-Driven One-Shot Unsupervised Domain Adaptation

Davila Carrazco, Julio Ivan; Kadam, Suvarna; Morerio, Pietro; Del Bue, Alessio; Murino, Vittorio

14:00 – 16:00

An AI-Driven Prototype for Groundwater Level Prediction: Exploring the Gorgovivo Spring Case Study

Galdelli, Alessandro; Narang, Gagan; Migliorelli, Lucia; Izzo, Domenico Antonio; Mancini, Adriano; Zingaretti, Primo

14:00 – 16:00

Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training

Lazzaro, Dario; Cinà, Antonio E; Pintor, Maura; Demontis, Ambra; Biggio, Battista; Roli, Fabio; Pelillo, Marcello

14:00 – 16:00

SynthCap: Augmenting Transformers with Synthetic Data for Image Captioning

Caffagni, Davide; Barraco, Manuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita

14:00 – 16:00

Weak Segmentation-Guided GAN for realistic color edition

Auriau, Vincent; Malherbe, Emmanuel; Perrot, Matthieu

14:00 – 16:00

Augmentation based on artificial occlusions for resilient instance segmentation

Kilis, Nikolaos; Tsipouridis, Grigorios; Karakostas, Iason; Dimitriou, Nikolaos; Tzovaras, Dimitrios

14:00 – 16:00

Hierarchical Pretrained Backbone Vision Transformer for Image Classification in Histopathology

Zedda, Luca; Loddo, Andrea; Di Ruberto, Cecilia

14:00 – 16:00

Real-Time GAN-based Model for Underwater Image Enhancement

Avola, Danilo; Cannistraci, Irene; Cascio, Marco; Cinque, Luigi; Diko, Anxhelo; Distante, Damiano; Foresti, Gian Luca; Mecca, Alessio; Scagnetto, Ivan

14:00 – 16:00

Depth camera face recognition by normalized fractal encodings

Bilotti, Umberto; Bisogni, Carmen; Nappi, Michele; Pero, Chiara

14:00 – 16:00

End-to-End Asbestos Roof Detection on Orthophotos Using Transformer-based YOLO Deep Neural Network

Pace, Cesare Davide; Bria, Alessandro; Focareta, Mariano; Lozupone, Gabriele; Marrocco, Claudio; Meoli, Giuseppe; Molinara, Mario

14:00 – 16:00

A Large-scale Analysis of Athletes’ Cumulative Race Time in Running Events

Freire Obregon, David; Lorenzo-Navarro, Javier; Santana, Oliverio J.; Hernandez-Sosa, Daniel; Castrillón-Santana, Modesto

14:00 – 16:00

HERO: A Multi-Modal Approach on Mobile Devices for Visual-Aware Conversational Assistance in Industrial Domains

Bonanno, Claudia; Ragusa, Francesco; Furnari, Antonino; Farinella, Giovanni Maria

14:00 – 16:00

Hand Gesture Recognition exploiting Handcrafted Features and LSTM

Avola, Danilo; Cinque, Luigi; Emam, Emad; Fontana, Federico; Foresti, Gian Luca; Marini, Marco Raoul; Pannone, Daniele

14:00 – 16:00

Enhancing PFI Prediction with GDS-MIL: A Graph-based Dual Stream MIL Approach

Bontempo, Gianpaolo; Bartolini, Nicola; Lovino, Marta; Bolelli, Federico; Virtanen, Anni; Ficarra, Elisa

14:00 – 16:00

Lightweight Blur Kernel Estimation Network for Blind Image Super-Resolution

Khan, Asif Hussain; Muhammad Umer, Rao; Dunnhofer, Matteo; Micheloni, Christian; Martinel, Niki

14:00 – 16:00

Enhancing Hierarchical Vector Quantized Autoencoders for Image Synthesis through Multiple Decoders

Serez, Dario; Cristani, Marco; Murino, Vittorio; Del Bue, Alessio; Morerio, Pietro

14:00 – 16:00

Specialise to Generalise: the Person Re-identification Case

Putzu, Lorenzo; Loddo, Andrea; Delussu, Rita; Fumera, Giorgio

14:00 – 16:00

Medical Transformers for Boosting Automatic Grading of Colon Carcinoma in Histological Images

Leo, Marco; Carcagni', Pierluigi; Signore, Luca; Distante, Cosimo

14:00 – 16:00

Exploiting Exif Data to Improve Image Classification using Convolutional Neural Networks

Bullin, Martin; Lederer, Ralf; Henrich, Andreas

14:00 – 16:00

Extrinsic Calibration of Multiple Depth Cameras for 3D Face Reconstruction

Burger, Jacopo; Facchi, Giuseppe; Grossi, Giuliano; Lanzarotti, Raffaella; Pedersini, Federico; Tartaglia, Gianluca

14:00 – 16:00

Not with my name! Inferring artists' names of input strings employed by Diffusion Models

Leotta, Roberto; Giudice, Oliver; Guarnera, Luca; Battiato, Sebastiano

14:00 – 16:00

MC-GTA: A Synthetic Benchmark for Multi-Camera Vehicle Tracking

Ciampi, Luca; Messina, Nicola; Valenti, Gaetano Emanuele; Amato, Giuseppe; Falchi, Fabrizio; Gennaro, Claudio

14:00 – 16:00

Spatial Exploration Indicators in the Remote Assessment of Visual Neglect

Ferraro, Federica; Iaconi, Giulia; Genesio, Giulia; Truffelli, Romina; Amella, Roberta; Simonini, Marina; Dellepiane, Silvana

Poster session 2

14:00 – 16:00

BHAC-MRI: Backdoor & Hybrid Attacks on MRI Brain Tumor Classification Using CNN

Imran, Muhammad; Qureshi, Hassaan Khaliq; Amerini, Irene

14:00 – 16:00

Time-aware Circulant Matrices for Question-based Temporal Localization

Bruni, Pierfrancesco; Falcon, Alex; Radeva, Petia

14:00 – 16:00

Image Retrieval in Semiconductor Manufacturing

Gatta, Giuseppe Gianmarco; Carrera, Diego; Rossi, Beatrice; Fragneto, Pasqualina; Boracchi, Giacomo

14:00 – 16:00

LieToMe: An LSTM-based Method for Deception Detection by Hand Movements

Avola, Danilo; Cinque, Luigi; De Marsico, Maria; Di Mambro, Angelo; Fagioli, Alessio; Foresti, Gian Luca; Lanzino, Romeo; Scarcello, Francesco

14:00 – 16:00

DiffDefense: Defending against Adversarial Attacks via Diffusion Models

Silva, Hondamunige Prasanna; Seidenari, Lorenzo; Del Bimbo, Alberto

14:00 – 16:00

OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data

Cartella, Giuseppe; Baldrati, Alberto; Morelli, Davide; Cornia, Marcella; Bertini, Marco; Cucchiara, Rita

14:00 – 16:00

An Optimized Pipeline for Image-Based Localization in Museums from Egocentric Images

Messina, Nicola; Falchi, Fabrizio; Furnari, Antonino; Gennaro, Claudio; Farinella, Giovanni Maria

14:00 – 16:00

Obstacle Avoidance and Interaction in Extended Reality: An Approach based on 3D Object Detection

Martini, Matteo; Chessa, Manuela; Solari, Fabio

14:00 – 16:00

Two is Better than One: Achieving High-Quality 3D Scene Modeling with a NeRF Ensemble

Di Sario, Francesco; Renzulli, Riccardo; Tartaglione, Enzo; Grangetto, Marco

14:00 – 16:00

Buffer-MIL: Robust Multi-instance Learning with a Buffer-based Approach

Bontempo, Gianpaolo; Lumetti, Luca; Porrello, Angelo; Bolelli, Federico; Calderara, Simone; Ficarra, Elisa

14:00 – 16:00

Automatic Generation of Semantic Parts for Face Image Synthesis

Fontanini, Omaso; Ferrari, Claudio; Bertozzi, Massimo; Prati, Andrea

14:00 – 16:00

GLR: Gradient-based Learning Rate scheduler

Napoli Spatafora, Maria Ausilia; Ortis, Alessandro; Battiato, Sebastiano

14:00 – 16:00

Spatial Transformer Generative Adversarial Network for Image Super-Resolution

Rempakos, Pantelis; Vrigkas, Michalis; Plissiti, Marina; Nikou, Christophoros

14:00 – 16:00

Smoothing and Transition Matrices estimation to learn with Noisy Labels

Ricci, Simone; Uricchio, Tiberio; Del Bimbo, Alberto

14:00 – 16:00

A Learnable EVC Intra Predictor using Masked Convolutions

Spadaro, Gabriele; Iacoviello, Roberto; Mosca, Alessandra; Valenzise, Giuseppe; Fiandrotti, Attilio

14:00 – 16:00

Many-to-Many metrics: a new approach to evaluate the performance of structural damage detection networks

Dondi, Piercarlo; Senaldi, Ilaria; Lombardi, Luca; Piastra, Marco

14:00 – 16:00

FEAD-D: Facial Expression Analysis in Deepfake Detection

Gravina, Michela; Galli, Antonio; De Micco, Geremia; Marrone, Stefano; Fiameni, Giuseppe; Sansone, Carlo

14:00 – 16:00

A Deep Learning based Approach for Synthesizing Realistic Depth Maps

Suarez, Patricia L; Carpio, Dario; Sappa, Angel

14:00 – 16:00

Exploring Audio Compression as Image Completion in Time-Frequency Domain

Scodeller, Giovanni; Pistellato, Mara; Bergamasco, Filippo

14:00 – 16:00

Combining identity features and artifact analysis for Differential Morphing Attack Detection

Di Domenico, Nicolò; Borghi, Guido; Franco, Annalisa; Maltoni, Davide

14:00 – 16:00

UAV Multi-Object Tracking by combining two Deep Neural Architectures

Manica, Alessandro; Mazzeo, Pier Luigi; Distante, Cosimo

14:00 – 16:00

MOVING: a MOdular and flexible platform for embodied VIsual NaviGation

Rosano, Marco; Ragusa, Francesco; Furnari, Antonino; Farinella, Giovanni Maria

14:00 – 16:00

Budget-Aware Pruning for Multi-Domain Learning

Dos Santos, Samuel Felipe; Berriel, Rodrigo F; Oliveira-Santos, Thiago; Sebe, Nicu; Almeida, Jurandy

14:00 – 16:00

Deepfakes Audio Detection leveraging audio spectrogram and Convolutional Neural Networks

Majid, Taiba; Amerini, Irene

14:00 – 16:00

A Computer Vision-Based water level monitoring system for touchless and sustainable water dispensing

Felicetti, Andrea; Paolanti, Marina; Pietrini, Rocco; Mancini, Adriano; Zingaretti, Primo; Frontoni, Emanuele

14:00 – 16:00

Benchmarking of Blind Video Deblurring Methods on Long Exposure and Resource Poor Settings

Napoli Spatafora, Maria Ausilia; Spata, Massimo O; Guarnera, Luca; Ortis, Alessandro; Battiato, Sebastiano

14:00 – 16:00

Compensation for Patient Movements in CBCT Imaging for Dental Applications

Asraf Ali, Abdul Salam Rasmi; Sarti, Cristina; Landi, Claudio

Poster session 3

14:00 – 16:00

Autism spectrum disorder identification from visual exploration of images

Bolpagni, Marco; Setti, Francesco

14:00 – 16:00

Fuzzy Logic Visual Network (FLVN): A neuro-symbolic approach for visual features matching

Manigrasso, Francesco; Morra, Lia; Lamberti, Fabrizio

14:00 – 16:00

HMPD: a novel dataset for microplastics classification with digital holography

Del Coco, Marco; Paturzo, Melania; Distante, Cosimo; Cacace, Teresa; Cocca, Mariacristina; Carcagni', Pierluigi

14:00 – 16:00

Uncovering Lies: Deception Detection in a Rolling-Dice Experiment

Dinges, Laslo; Fiedler, Marc; Al-Hamadi, Ayoub; Abdelrahman, Ahmed; Weimann, Joachim; Bershadskyy, Dmitri

14:00 – 16:00

Annotating the Inferior Alveolar Canal: the Ultimate Tool

Lumetti, Luca; Pipoli, Vittorio; Bolelli, Federico; Grana, Costantino

14:00 – 16:00

Towards Explainable Navigation and Recounting

Poppi, Samuele; Rawal, Niyati; Bigazzi, Roberto; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita

14:00 – 16:00

The Specchieri MarVen Dataset: an Abbreviation-rich Dataset in Venetian Idiom

Ferro, Sara; Pasquariello, Debora; Pelillo, Marcello; Traviglia, Arianna

14:00 – 16:00

Consensus Ranking for Efficient Face Image Retrieval: A Novel Method for Maximising Precision and Recall

Hast, Anders

14:00 – 16:00

Improved Bilinear Pooling For Real-Time Pose Event Camera Relocalisation

Tabia, Ahmed

14:00 – 16:00

An unsupervised learning approach to resolve phenotype to genotype mapping in budding yeasts vacuoles

Pastore, Vito Paolo; Alfano, Paolo D; Oke, Ashwini; Capponi, Sara; Elnatan, Daniel; Woodruff-Madeira, Xavier; Nguyen, Anita; Fung, Jennifer; Bianco, Simone

14:00 – 16:00

FERMOUTH: Facial Emotion Recognition from the MOUTH region

De Carolis, Berardina; Macchiarulo, Nicola; Palestra, Giuseppe; De Matteis , Alberto Pio; Lippolis, Andrea

14:00 – 16:00

LCMV: Lightweight Classification Module for Video Domain Adaptation

Neubert, Julian; Planamente, Mirco; Plizzari, Chiara; Caputo, Barbara

14:00 – 16:00

Video Sonification to Support Visually Impaired People: the VISaVIS approach

Onofrei, Marius; Castellini, Fabio; Pravadelli, Graziano; Drioli, Carlo; Setti, Francesco

14:00 – 16:00

Dynamic Local Filters in Graph Convolutional Neural Networks

Apicella, Andrea; Isgrò, Francesco; Pollastro, Andrea; Prevete, Roberto

14:00 – 16:00

Shallow camera pipeline for night photography enhancement

Zini, Simone; Rota, Claudio; Buzzelli, Marco; Bianco, Simone; Schettini, Raimondo

Industrial poster session

14:00 – 16:00

Instance segmentation applied to underground infrastructures

Haenel, Raphaël; Semler, Quentin; Semin, Edouard; Tabbone, Antoine Salvatore; Grussenmeyer, Pierre

14:00 – 16:00

Generating Invariance-based Adversarial Examples: Bringing Humans Back Into the Loop

Merkle, Florian; Nocker, Martin; Schöttle, Pascal; Sirbu, Mihaela-Roxana

14:00 – 16:00

MARS: Mask Attention Refinement with Sequential Quadtree Nodes for Car Damage Instance Segmentation

Panboonyuen, Teerapong; Nithisopa, Naphat; Pienroj, Panin; Jirachuphun, Laphonchai; Watthanasirikrit, Chaiwasut; Pornwiriyakul, Naruepon

14:00 – 16:00

On-Device Learning with Binary Neural Networks

Vorabbi, Lorenzo; Maltoni, Davide; Santi, Stefano

14:00 – 16:00

Towards One-Shot PCB Component Detection with YOLO

Spadaro, Gabriele; Vetrano, Gaspare; Penna, Barbara; Serena, Antonio; Fiandrotti, Attilio

14:00 – 16:00

Wildfires Classification: A Comparative Study

Cruciata, Giorgio; Lo Presti, Liliana; Ajello, Gabriele; Cicero, Paolo; Corvisieri, Giacomo; La Cascia, Marco

14:00 – 16:00

A General Purpose Method for Image Collection Summarization and Exploration

Leonardi, Marco; Napoletano, Paolo; Rozza, Alessandro; Schettini, Raimondo

14:00 – 16:00

Automated Identification of Failure Cases in Organ at Risk Segmentation Using Distance Metrics: A Study on CT Data

Honarmandi Shandiz, Amin; Radics, Attila; Tamada, Rajesh Kumar; Makk, Arpad; Glowacka, Karolina; Ferenczi, Lehel; Dutta, Sandeep; Fanariotis, Michail

14:00 – 16:00

Digitizer: A Synthetic Dataset for Well-Log Analysis

Nasim, Quamer; Patwardhan, Narendra; Ali, Javed; Maiti, Tannistha; Marrone, Stefano; Singh, Tarry; Sansone, Carlo

14:00 – 16:00

CNN-BLSTM Model for Arabic Text Recognition in Unconstrained Captured Identity Documents

Ghanmi, Nabil; Belhakimi, Amine; Awal, Ahmad-Montaser

Presentation Instructions

The conference is held in presence. There will be no streaming. All presentations are onsite. 

Oral presentations

• Oral talks are given 20 minutes. Since the sessions are packed, this will be strictly enforced. You must leave the podium once your time is up.

• Additional 4 minutes are allocated for questions by the session chairs, switching between speakers and introducing the next speaker.

• Oral presenters will use their own laptop.

• The projector have a HDMI connector and is setup for the 16:10  format using a 1920x1200 resolution.

Poster presentation

• Poster stands have a dimension of 85cm (width) x 185cm (height). You can use any poster size within these bounds, but we recommend using a portrait A0 layout.

• After the poster session ends, please remove the poster to leave the space for the next presenter.