ICIAP2019 

 20th International Conference on 

 IMAGE ANALYSIS AND PROCESSING 

 Trento, 9-13 September, 2019 

ICIAP 2019 is the 20th edition of a series of conferences organized biennially by the Italian Member Society (CVPL, ex GIRPR) of the International Association for Pattern Recognition (IAPR).

The focus of the conference is on both classic and recent trends in computer vision, pattern recognition and image processing, and covers both theoretical and applicative aspects, with particular emphasis on the following topics:

Video Analysis & Understanding, Pattern Recognition and Machine Learning, Deep Learning, Multiview Geometry and 3D Computer Vision, Image Analysis, Detection and Recognition, Multimedia, Biomedical and Assistive Technology, Digital Forensics, Image Processing for Cultural Heritage.

Springer Proceedings are now available from the URLs below. Access will be free for all registered conference participants for the period  September 7 to October 7, 2019.

Workshop proceedings are available from the URL below:

 Important Dates 

Workshop and Tutorial
September 9th — 10th, 2019

Main Conference
September 11th — 13th, 2019

Full paper submission
The deadline has been postponed to May 6th, 2019

Full paper evaluation notification
June 24th, 2019

Camera ready submission
July 12th, 2019

 Program 

The program guide and summary table are available now:

Guide (PDF | 1.7 MB )

Table (PDF | 59 kB )

 Program Summary 

Monday, September 9

09:00 – 11:00         Workshop W1 + Tutorials T1 and T2
11:00 – 11:30         Coffee break
11:30 – 13:00         Workshop W1 + Tutorials T3 and T4
13:00 – 14:30         Lunch break
14:30 – 16:30         Workshop W1 + Tutorial T5
16:30 – 17:00         Coffee break
17:00 – 19:00         Workshop W1


Tuesday, September 10

09:00 – 11:00         Workshop W2 and W3 + Industrial Session
11:00 – 11:30         Coffee break
11:30 – 13:00         Workshop W2 and W3 + Industrial Session
13:00 – 14:30         Lunch break
14:30 – 16:30         Workshop W4 + Tutorial T6 + Industrial Session
16:30 – 17:00         Coffee break
17:00 – 19:00         Workshop W4 
20:00 – 22:30         Welcome Reception at Buonconsiglio Castle


Wednesday, September 11

08:45 – 09:00          Welcome
09:00 – 10:00          Invited Talk 1: Davide Scaramuzza
10:00 – 11:00          Oral 1
11:00 – 11:30          Poster 1 + Coffee break
11:30 – 13:00          Poster 1 
13:00 – 14:30          Lunch break
14:30 – 15:30          Oral 2 - Image Analysis, Detection and Recognition
15:30 – 16:00          Spotlight 1
16:00 – 16:30          DAFNE Challenge Session
16:30 – 17:00          Poster 2 + Coffee break
17:00 – 18:30          Poster 2 


Thursday, September 12

09:00 – 10:00          Invited Talk 2: Ayellet Tal
10:00 – 11:00          Oral 3 - Deep Learning
11:00 – 11:30          Coffee break
11:30 – 12:30          Oral 4 - Brave New Ideas
12:30 – 13:00          Spotlight 2
13:00 – 14:30          Lunch break
14:30 – 16:30          Poster 3
16:30 – 17:00          Coffee Break
17:00 – 19:00          CVPL Meeting
20:00 – 22:30          Conference Banquet at Villa Bortolazzi (Villa Bortolazzi is located in Mattarello, a small village at 20 minutes of distance from the Conference venue. A bus service will bring the conference participants to the banquet venue and back to the conference venue. The first bus to Villa Bortolazzi will leave from Via Torre Vanga, 28 at 19:30, the second one at 19:45.)


Friday, September 13

09:00 – 09:45          Invited Talk 3: Emanuele Rodolà
09:45 – 10:30          Invited Talk 4: Alessandra Sciutti
10:30 – 11:00          CVPL Highlights 1 
11:00 – 11:30          Coffee break
11:30 – 12:00          CVPL Highlights 2
12:00 – 13:00          Oral 5 - Applications
13:00 – 14:30          Lunch break
14:30 – 16:30          Poster 4

 Invited Talks 

Invited Talk 1: Davide Scaramuzza

Autonomous, Agile, Vision-controlled Drones: from Frame to Event Vision

When:Wednesday, September 11, 09:00 - 10:00
Where: Sala 1

Abstract:  Autonomous quadrotors will soon play a major role in search-and-rescue and remote-inspection missions, where a fast response is crucial. Quadrotors have the potential to navigate quickly through unstructured environments, enter and exit buildings through narrow gaps, and fly through collapsed buildings. However, their speed and maneuverability are still far from those of birds. Indeed, agile navigation through unknown, indoor environments poses a number of challenges for robotics research in terms of perception, state estimation, planning, and control. In this talk, I will show that active vision is crucial in order to plan trajectories that improve the quality of perception. Also, I will talk about our recent results on event based vision to enable low latency sensory motor control and navigation in low light and high dynamic environment, where traditional vision sensor fail.

Bio: Davide Scaramuzza (born in 1980, Italian) is Professor of Robotics and Perception at both departments of Informatics (University of Zurich) and Neuroinformatics (ETH Zurich and University of Zurich), where he does research at the intersection of robotics and computer vision. He did his PhD in robotics and computer vision at ETH Zurich and a postdoc at the University of Pennsylvania. From 2009 to 2012, he led the European project sFly, which introduced the PX4 autopilot (used in half a million commercial drones today) and pioneered vision-based autonomous navigation of micro drones. For his research contributions, he was awarded the prestigious IEEE Robotics and Automation Early Career Award, the SNSF-ERC Starting Grant, a Google, Qualcomm, and INTEL awards, and several paper awards. He coauthored the book "Introduction to Autonomous Mobile Robots" (published by MIT Press; 10,000 copies sold) and more than 100 papers on robotics and perception. He has served as a consultant for the United Nations (UN) International Atomic Energy Agency (IAEA) Fukushima Action Plan on Nuclear Safety, and several drone and computer-vision companies. In 2015, he cofounded Zurich-Eye, which later became Facebook-Oculus Zurich. 
Many aspects of his research have been prominently featured in the popular press, such as Discovery Channel, BBC, The New York Times, IEEE Spectrum, MIT Technology Review Magazine.

Invited Talk 2: Ayellet Tal

Past Forward: When Computer Vision and Archaeology Meet

When: Thursday, September 12 , 09:00 - 10:00
Where: Sala 1

Abstract: Technology is the symbol of our age. Nevertheless, some fields have been left out of the revolution. One of these is archaeology, where many tasks are still performed manually - from the initial excavation, through documentation, to restoration. It turns out that some of these activities are classical computer vision tasks, such as puzzle solving, shape completion, matching and edge detection. The objects, however, are much harder to deal with than usual, since they are broken and eroded after laying underground for thousands of years. Therefore, being able to handle these objects benefits not only archaeology, but also computer vision. In this talk I will describe some of the algorithms we have developed to replace manual restoration.

Bio: Ayellet Tal is a professor in the Department of Electrical Engineering and heads the Computer Graphics and Multimedia Lab at the Technion, Israel. She holds a Ph.D. in Computer Science from Princeton University and a B.Sc degree (Summa cum Laude) in Mathematics and Computer Science from Tel-Aviv University. Her research interests span computer graphics, computer vision and information visualization. She regularly serves as an area chair and as a member of program committees of the major international conferences and as an associate editor of journals.

Invited Talk 3: Emanuele Rodolà

Hearing the shape of things

When:Friday, September 13, 09:00 - 09:45
Where: Sala 1

Abstract:  Spectral geometry is at the heart of a variety of problems in computer vision, graphics, pattern recognition and machine learning. Ultimately, the core reason for its success can be traced down to questions of stability and informativeness of the eigenvectors and eigenvalues of certain operators. In this talk, I will discuss and show tangible examples of such properties, and showcase some dramatic implications on a selection of notoriously hard problems in computer vision and graphics. First, I will address the question whether one can recover the shape of a geometric object from its vibration frequencies (‘hear the shape of the drum’); while theoretically the answer to this question is negative, little is known about the practical possibility of using the spectrum for shape reconstruction and optimization. I will introduce a numerical procedure called isospectralization, showing how this *practical* problem is solvable. Then, I will discuss the widespread problem of data corruption and partiality, and demonstrate how knowledge of the behavior of the spectral decomposition of Laplacians can lead to unprecedented results as exemplified on partial dense correspondence of deformable 3D shapes. I will conclude my talk with an overview of current and future work in these areas, with a look at potential applications in computational biology, computer-assisted medical diagnosis, and deep learning.

Bio:  Emanuele Rodolà is a tenured professor of computer science at Sapienza University of Rome, where he leads the Geometric and Visual Computing group funded by an ERC Starting Grant (2018-). Previously, he held positions at USI Lugano, TU Munich, and the University of Tokyo under various fellowships. He holds or has held visiting positions at Tel Aviv University, Technion, Ecole polytechnique, Harvard, and Stanford. He received best paper awards at 3DPVT 2010, VMV 2015, and SGP 2016, has been serving since 2010 in the program committees of CVPR, ICCV, ECCV, etc., has been serving as Area Chair at 3DV since 2016, founded and chaired several successful workshops including the IEEE workshop on Geometry Meets Deep Learning, organized multiple SHREC contests, and was recognized 8 times as IEEE Outstanding Reviewer. He gave tutorials and short courses in multiple occasions at ECCV, EUROGRAPHICS, SGP, SIGGRAPH, and SIGGRAPH Asia. His work on 3D reconstruction was featured by the national Italian television (RAI) in 2012. His research focuses on spectral geometry processing, 3D computer vision and geometric deep learning, and has published more than 60 papers in these areas.

Invited Talk 4: Alessandra Sciutti

Cognitive Vision for Human Robot Interaction

When:Friday, September 13, 09:45 - 10:30
Where:Sala 1

Abstract: Society is expecting robots to enter our houses and factories tomorrow, with the aim of cooperating with us. For this goal to be achievable, it is necessary that these agents become primarily cognitive systems, endowed with a cognitive architecture that enables them to adapt, predict, and pro-actively interact with the environment and the human partners. In this framework, vision needs to be cognitive: purposive, adaptive and anticipatory. Furthermore an artificial cognitive visual system which aims at existing and thriving in a human society needs the ability to communicate. 
Human communication is based on mutual understanding: I know how to communicate because I entertain a model of you, which enables me to select an effective way to convey to you what I want and to have an intuition of your internal states – what you need, fear or desire. Such intuition guides my vision, enabling me to perceive properties that would be otherwise not accessible to my perception, as goals, emotions or effort.
Our contribution to the roadmap toward cognitive vision systems leverages on the use of a humanoid robot (iCub) to try and test some of our assumptions on how to build a cognitive interactive agent. We attempt at modeling the minimal skills necessary for cognitive development, focusing on the visual features that enable to recognize the presence of other agents in the scene, to allow action matching across different visual perspectives and to foster automatic speed adaptation in human-robot interactive repetitive tasks. We investigate how a robot could leverage on visual signals to anticipate the partner’s goals for collaborative or competitive purposes, to infer the right moment to interact and to assess the emotional reactions of the partners.  
In a dual approach we are trying to understand how to modulate robot behavior to elicit better human understanding and to express different characteristics of the interaction: from the mood to the level of commitment. This approach is propaedeutic to the creation of a cognitive vision system, by helping in the definition of what is relevant to attend to, starting from signals originating from the intrinsic characteristics of the human body. 
We believe that only a structured effort toward cognitive vision – or better visually-enabled cognition – will in the future allow for more humane machines, able to see the world and people as we do and engage with them in a meaningful manner. 

Bio: Alessandra received her Ph.D. in Humanoid Technologies from the University of Genoa (Italy) in 2010. After a Post Doc at theIstituto Italiano di Tecnologia (IIT) and two research periods in USA and Japan, she became the scientific responsible of the Cognitive Robotics and Interaction Laboratory of the RBCS Dept. at IIT. After being Assistant Professor in Bioengineering at DIBRIS University of Genoa, she is now Tenure-Track Researcher at theIstituto Italiano di Tecnologia, head of the COgNiTive Architecture for Collaborative Technologies (CONTACT) unit. In 2018 she has been awarded the ERC Starting Grant wHiSPER, focused on the investigation of joint perception between humans and robots. She published more than 60 papers and abstracts and participated in the coordination of the CODEFROR European IRSES project. She is an Associate Editor of Robots and Autonomous Systems, Cognitive Systems Research and the International Journal of Humanoid Robotics and she has served as a member of the Program Committee for the International Conference on Human-Agent Interaction and IEEE International conference on Development and Learning and Epigenetic Robotics.  The scientific aim of her research is to investigate the sensory and motor mechanisms underlying mutual understanding in human-human and human-robot interaction.

 Main Conference 

Wednesday morning · September 11, 2019

Oral 1 · 10:00 – 11:00

Drone Patrolling with Reinforcement LearningClaudio Piciarelli, Gian Luca Foresti
Automatic Generation of Waypoint Graphs from Distributed Ceiling-Mounted Smart Cameras for Decentralized Multi-Robot Indoor NavigationChristophe Bobda, Andrew Felder, Dillon VanBuskirk
RE-OBJ: Jointly Learning the Foreground and Background for Object Instance Re-IdentificationVaibhav Bansal, Stuart James, Alessio Del Bue
Open Set Recognition for Unique Person Counting via Virtual GatesFrancesco Turchini, Matteo Bruni, Claudio Baecchi, Tiberio Uricchio, Alberto Del Bimbo

 

Poster 1 · 11:00 – 13:00

1Artpedia: A New Visual-Semantic Dataset with Visual and Contextual Sentences in the Artistic DomainMatteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Massimiliano Corsini, Rita Cucchiara
2An Efficient Approximate kNN Graph Method for Diffusion on Image RetrievalFederico Magliani, Kevin McGuinness, Eva Mohedano, Andrea Prati
3Label Propagation Guided by Hierarchy of Partitions for Superpixel ComputationCarolina Jeronimo, Jean Cousty, Benjamin Perret, Zenilton Patrocinio Jr, Silvio Guimaraes
4Manual Annotations on Depth Maps for Human Pose EstimationAndrea D'Eusanio, Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara
5Disparity Image Analysis for 3D Characterization of Surface AnomaliesR. Marani, A. Petitti, M. Attolico, G. Cicirelli, A. Mirella, Tiziana D'Orazio
6Lightweight Deep Learning Pipeline for Detection, Segmentation and Classification of Breast Cancer AnomaliesHugo S. Oliveira
7Geometry-based Skin Colour Estimation for Bare Torso Surface ReconstructionJoao Pedro Monteiro, Hooshiar Zolfagharnasab, Helder Pinto de Oliveira
8A Single-Resolution Fully Convolutional Network for Retinal Vessel Segmentation in Raw Fundus Images
Ricardo J. Araujo
9Low-Complexity Scene Understanding NetworkLivia A. Iordache, Vlad Paunescu, Andrei S. Leica, ByeongMoon Jeon, Wonjun Kang, Joonhyung Kwon
10Image Anomaly Detection with Capsule Networks and Imbalanced DatasetsClaudio Piciarelli, Pankaj Mishra, Gian Luca Foresti
11Improving Facial Emotion Recognition Systems with Crucial Feature Extractors
Ram K. Pandey, Souvik Karmakar, Ramakrishnan A. G., Nabagata Saha
12A Region Proposal Approach for Cells Detection and Counting from Microscopic Blood Images
Andrea Loddo, Cecilia Di Ruberto, Lorenzo Putzu
13Personalized Expression Synthesis Using A Hybrid Geometric-Machine Learning MethodSarra Zaied, Catherine Soladie, Pierre-Yves Richard
14Easing Function as a Tool of Color Correction for Display Stitching in Virtual RealityDariusz Sawicki, Agnieszka Wolska, Mariusz Wiselka, Szymon Ordysinski
15Towards Multiple Sources Semantic SegmentationPaolo Russo, Tatiana Tommasi, Barbara Caputo
16On Image Enhancement for Unsupervised Image Description and MatchingMichela Lecca, Alessandro Torresani, Fabio Remondino
17A Novel Anomaly Score for Isolation ForestsAntonella Mensi, Manuele Bicego
18Learning Pedestrian Detection from VirtualWorldsGiuseppe Amato, Luca Ciampi, Fabrizio Falchi, Claudio Gennaro, Nicola Messina
19Sentiment Analysis from Images of Natural DisastersKashif Ahmad, Zohaib Hassan, Nicola Conci, Ala Al-Fuqaha
20Adaptive Hybrid Representation for Graph-Based Semi-supervised ClassificationFadi Dornaika, Alireza Bosaghzadeh 
21Real-time Neurodegenerative Disease Video Classification with Severity PredictionVincenzo Dentamaro, Donato Impedovo, Giuseppe Pirlo 
22Gesture Recognition by Leap Motion Controller and LSTM Networks for CAD-oriented InterfacesLisa Mazzini, Annalisa Franco, Davide Maltoni 
23VEDI: Vision Exploitation for Data InterpretationGiovanni Maria Farinella, Giovanni Signorello, Sebastiano Battiato, Antonino Furnari, Francesco Ragusa, Rosario Leonardi, Emanuele Ragusa, Emanuele Scuderi, Antonino Lopes, Luciano Santo, Marina Samarotto
24Thick Line Segment Detection with Fast Directional Tracking
Philippe Even, Hoai Ngo, Bertrand Kerautret
25SWIR Camera-Based Localization and Mapping in Challenging Environments
Viachaslau Kachurka, David Roussel, Hicham Hadj-Abdelkader, Fabien Bonardi, Jean-Yves Didier, Samia Bouchafa

 

Wednesday afternoon · September 11, 2019

Oral 2 · Image Analysis, Detection and Recognition · 14:30 – 15:30

Relation, Transition and Comparison between the Adaptive Nearest Neighbor Rule and the Hypersphere ClassifierMauricio Orozco-Alzate, Sisto Baldo, Manuele Bicego
Texture Retrieval in the Wild through Detection-based AttributesChristian Joppi, Marco Godi, Andrea Giachetti, Fabio Pellacini, Marco Cristani
Autocropping: A Closer Look at Benchmark DatasetsLuigi Celona, Gianluigi Ciocca, Paolo Napoletano, Raimondo Schettini
Domain Adaptation for Privacy-preserving Person Detection in Thermal ImageryMy Kieu, Andy Bagdanov, Marco Bertini, Alberto Del Bimbo

 

Spotlight 1 · 15:30 – 16:00

Hand Detection using Zoomed Neural NetworksSergio R. Cruz, Antoni Chan
Wafer Defect Map Classification Using Sparse Convolutional NetworksRoberto Di Bella, Diego Carrera, Beatrice Rossi, Pasqualina Fragneto, Giacomo Boracchi
Video-Based Convolutional Attention for Person Re-IdentificationMarco Zamprogno, Marco Passon, Niki Martinel, Giuseppe Serra, Giuseppe Lancioni, Christian Micheloni, Carlo Tasso, Gian Luca Foresti
GADA: Generative Adversarial Data Augmentation for Image Quality AssessmentPietro Bongini, Riccardo Del Chiaro, Andy Bagdanov, Alberto Del Bimbo
Variational Autoencoder inspired by Brain's Convergence-Divergence Zones for Autonomous Driving ApplicationAlice Plebe, Mauro Da Lio
Learning an Optimisable Semantic Segmentation Map with Image Conditioned Variational AutoencoderPengcheng Zhuang, Yusuke Sekikawa, Hideo Saito
3D Shape Segmentation with Geometric Deep Learning

Davide Boscaini, Fabio Poiesi

3TP-CNN: Radiomics and Deep Learning for Lesions Classification in DCE-MRIMichela Gravina, Stefano Marrone, Gabriele Piantadosi, Mario Sansone, Carlo Sansone
Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANsVictor Ponce-Lopez, Tilo Burghardt, Yue Sun, Sion Hannuna, Dima Damen, Majid Mirmehdi

 

Poster 2 · 16:30 – 18:30

1Hand Detection using Zoomed Neural NetworksSergio R. Cruz, Antoni Chan
2Wafer Defect Map Classification Using Sparse Convolutional NetworksRoberto Di Bella, Diego Carrera, Beatrice Rossi, Pasqualina Fragneto, Giacomo Boracchi
3Video-Based Convolutional Attention for Person Re-IdentificationMarco Zamprogno, Marco Passon, Niki Martinel, Giuseppe Serra, Giuseppe Lancioni, Christian Micheloni, Carlo Tasso, Gian Luca Foresti
4GADA: Generative Adversarial Data Augmentation for Image Quality AssessmentPietro Bongini, Riccardo Del Chiaro, Andy Bagdanov, Alberto Del Bimbo
5Variational Autoencoder inspired by Brain's Convergence-Divergence Zones for Autonomous Driving ApplicationAlice Plebe, Mauro Da Lio
6Learning an Optimisable Semantic Segmentation Map with Image Conditioned Variational AutoencoderPengcheng Zhuang, Yusuke Sekikawa, Hideo Saito
73D Shape Segmentation with Geometric Deep LearningDavide Boscaini, Fabio Poiesi
83TP-CNN: Radiomics and Deep Learning for Lesions Classification in DCE-MRIMichela Gravina, Stefano Marrone, Gabriele Piantadosi, Mario Sansone, Carlo Sansone
9Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANsVictor Ponce-Lopez, Tilo Burghardt, Yue Sun, Sion Hannuna, Dima Damen, Majid Mirmehdi
10A Gradient-based Spatial Color Algorithm for Image Contrast EnhacementMichela Lecca
11Video synthesis from Intensity and Event Frames
Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara
12Active Two Phase Collaborative Representation Classifier for Image CategorizationFadi Dornaika, Youssof El Traboulsi, Yassine Ruichek
13Blind Image Quality Assessment based on the use of Saliency Maps and a Multivariate Gaussian DistributionChristophe Charrier, Hakim Saadane, Christine Fernandez-Maloigne
14A Graph-based Color Lines Model for Image AnalysisDavid Arturo Duque-Arias, Santiago Velasco-Forero, Jean-Emmanuel Deschaud, Francois Goulette, Beatriz Marcotegui 
15Take a Ramble into Solution Spaces for Classification Problems in Neural NetworksEnzo Tartaglione, Marco Grangetto 
16Evaluating Deep Convolutional Neural Networks as Texture Feature ExtractorsLeonardo Scabini, Rayner Condori, Lucas C. Ribas, Odemir Bruno 
17Unsupervised Domain Adaptation using Full-Feature Whitening and ColouringSubhankar Roy, Aliaksandr Siarohin, Nicu Sebe
18Frame Interpolation using Phase Information and Guided Image FilteringFahim Arif, Sundus Amin, Abdul Ghafoor, Mohsin Riaz
19Generalised Gradient Vector Flow for Content-aware Image ResizingTiziana Rotondo, Alessandro Ortis, Sebastiano Battiato
20Learning to Rank Food ImagesDario Allegra, Daniela Erba, Giovanni Maria Farinella, Giovanni Grazioso, Paolo Maci, Filippo Stanco, Valeria Tomaselli
21Supervised Two-Stage-TL on Imbalanced Dataset for Sport Classification
Tianyu Bi, Dmitri Jarnikov, Johan Lukkien
22A Block-Based Union-Find Algorithm to Label Connected Components on GPUs
Stefano Allegretti, Federico Bolelli, Michele Cancilla, Costantino Grana
23A New Descriptor for Keypoint-Based Background Modeling
Danilo Avola, Marco Bernardi, Marco Cascio, Luigi Cinque, Gian Luca Foresti, Cristiano C. Massaroni
24Preliminary Experiment of the Interactive Registration of a Trocar for Thoracoscopy with Hololens Headset
Christophe Lohou
25A Low-cost Computer Vision System for Real-time Tennis Analysis
Stefano Messelodi, Carla Maria Modena, Valerio Ropele, Stefano Marcon, Mario Sgro

 

Thursday morning · September 12, 2019

Oral 3 · Deep Learning · 10:00 – 11:00
Tackling Partial Domain Adaptation with Self-SupervisionSilvia Bucci, Antonio D'Innocente, Tatiana Tommasi
Hebbian Learning Meets Deep LearningGiuseppe Amato, Fabio Carrara, Fabrizio Falchi, Claudio Gennaro, Gabriele Lagani
Regularized Evolutionary Algorithm for Dynamic Neural Topology SearchCristiano Saltori, Subhankar Roy, Nicu Sebe, Giovanni Iacca
MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial ColorizationTomaso Fontanini, Eleonora Iotti, Andrea Prati
 
Oral 4 · Brave New Ideas · 11:30 – 12:30
Ontology-Driven Food Category Classification in ImagesIvan Donadello, Mauro Dragoni
Image-to-Image Translation to Unfold the Reality of Artworks: an Empirical AnalysisLatteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Image Memorability using Diverse Visual Features and Soft AttentionMarco Leonardi, Luigi Celona, Paolo Napoletano, Simone Bianco, Raimondo Schettini, Franco Manessi, Alessandro Rozza
 
Spotlight 2 · 12:30 – 13:00
Problems with Saliency MapsGiuseppe Boccignone, Vittorio Cuculo, Alessandro D'Amelio
Prediction of Social Image Popularity DynamicsAlessandro Ortis, Giovanni Maria Farinella, Sebastiano Battiato
Improving the Performance of Thinning Algorithms with Directed Rooted Acyclic GraphsFederico Bolelli, Costantino Grana
3DMM for Accurate Reconstruction of Depth DataClaudio Ferrari, Stefano Berretti, Pietro Pala, Alberto Del Bimbo
Mask Guided Fusion For Group Activity Recognition In ImagesArif Akar, Nazli Ikizler-Cinbis
Recognition of Human Activities in Daubechies Complex Wavelet DomainManish Khare
ActiVis: Mobile Object Detection and Active Guidance for People with Visual ImpairmentsJacobus C. Lock, Nicola Bellotto, Andrea Tramontano, Stefano Ghidoni
Vehicle Trajectories from Unlabeled Data through Iterative Plane RegistrationFederico Becattini, Lorenzo Seidenari, Lorenzo Berlincioni, Leonardo Galteri, Alberto Del Bimbo
Dimensionality Reduction using Discriminative Autoencoders for Remote Sensing Image RetrievalMohbat Tharani, Tooba Mukhtar, Numan Khurshid, Murtaza Taj

 

Thursday afternoon · September 12, 2019

Poster 3 · 14:30 – 16:30
1Problems with Saliency MapsGiuseppe Boccignone, Vittorio Cuculo, Alessandro D'Amelio
2Prediction of Social Image Popularity DynamicsAlessandro Ortis, Giovanni Maria Farinella, Sebastiano Battiato
3Improving the Performance of Thinning Algorithms with Directed Rooted Acyclic GraphsFederico Bolelli, Costantino Grana
43DMM for Accurate Reconstruction of Depth DataClaudio Ferrari, Stefano Berretti, Pietro Pala, Alberto Del Bimbo
5Mask Guided Fusion For Group Activity Recognition In ImagesArif Akar, Nazli Ikizler-Cinbis
6Recognition of Human Activities in Daubechies Complex Wavelet DomainManish Khare
7ActiVis: Mobile Object Detection and Active Guidance for People with Visual ImpairmentsJacobus C. Lock, Nicola Bellotto, Andrea Tramontano, Stefano Ghidoni
8Vehicle Trajectories from Unlabeled Data through Iterative Plane RegistrationFederico Becattini, Lorenzo Seidenari, Lorenzo Berlincioni, Leonardo Galteri, Alberto Del Bimbo
9Dimensionality Reduction using Discriminative Autoencoders for Remote Sensing Image RetrievalMohbat Tharani, Tooba Mukhtar, Numan Khurshid, Murtaza Taj
10View-invariant Pose Analysis for Human Movement Assessment from RGB DataFaegheh Sardari, Adeline Paiement, Majid Mirmehdi
11Hyperspectral Image Classification via Convolutional Neural Network based on Dilation LayersRami Reddy Devaram, Dario Allegra, Giovanni Gallo, Filippo Stanco
12A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized DocumentsIsaak Kavasidis, Carmelo Pino, Francesco Rundo, Daniela Giordano, Paolo Messina, Concetto Spampinato
13Training Efficient Semantic Segmentation CNNs on Multiple DatasetsMarco Leonardi, Davide Mazzini, Raimondo Schettini
14Estimation of Speed and Distance of Surrounding Vehicles from a Single CameraMirko Zaffaroni, Marco Grangetto, Alessandro Farasin
15Combining Saliency Estimation MethodsMarco Buzzelli, Simone Bianco, Gianluigi Ciocca
16Analysis of Dynamic Brain Connectivity Through Geodesic ClusteringMuhammad Aabubakar Yamin, Michael Dayan, Letizia Squarcina, Paolo Brambilla, Vittorio Murino, Vaibhav Diwadkar, Diego Sona
17A Decision Tree for Automatic Diagnosis of Parkinson's Disease from Offline Drawing Samples: Experiments and FindingsAntonio Parziale, Antonio Della Cioppa, Rosa Senatore, Angelo Marcelli
18The Impact of Padding on Image Classification by Using Pre-trained Convolutional Neural NetworksHongxiang Tang, Alessandro Ortis, Sebastiano Battiato
19Automatic Framework for Multiple Sclerosis Follow-up by Magnetic Resonance Imaging for Reducing Contrast AgentsGiuseppe Placidi, Luigi Cinque, Matteo Polsinelli, Alessandra Splendiani, Emanuele Tommasino
20Emotional State Recognition with Micro-Expressions and Pulse Rate VariabilityReda Belaiche, Rita Meziati Sabour, Cyrille Migniot, Yannick Benezeth, Dominique Ginhac, Keisuke Nakamura, Randy Gomez, Fan Yang
21Discovering Latent Domains for Unsupervised Domain Adaptation through ConsistencyMassimiliano Mancini, Lorenzo Porzi, Fabio Cermelli, Barbara Caputo
22Deep Motion Model for Pedestrian Tracking in 360 Degrees VideosLiliana Lo Presti, Marco La Cascia
23Single Image Super-Resolution for Optical Satellite Scenes using Deep Deconvolutional NetworkSumedh D. Pendurkar, Biplab Banerjee, Sudipan Saha, Francesca Bovolo
24Genuine Personality Recognition from Highly Constrained Face ImagesFabio Anselmi, Nicoletta Noceti, Lorenzo Rosasco, Robert Ward
25Automatic Segmentation based on Deep Learning Techniques for Diabetic Foot Monitoring through Multimodal ImagesAbian Hernandez, Natalia Arteaga-Marrero, Enrique Villa, Himar Fabelo, Gustavo M. Callico, Juan Ruiz-Alzola
26On Generative Modeling of Cell Shape Using 3D GANsDavid Wiesner, Tereza Necasova, David Svoboda
27Particle Filtering for Tracking in 360 degrees Videos using virtual PTZ CamerasVito Monteleone, Liliana Lo Presti, Marco La Cascia
28Feature-Based SLAM Algorithm for Small-Scale UAVs with Nadir ViewDanilo Avola, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti, Cristiano C. Massaroni, Daniele Pannone

 

Friday · September 13, 2019

Oral 5 · Applications · 12:00 – 13:00
Performance Evaluation of Learned 3D FeaturesRiccardo Spezialetti, Samuele Salti, Luigi Di Stefano
A Convolutional Neural Network for Virtual Screening of Molecular FingerprintsIsabella Mendolia, Salvatore Contino, Ugo Perricone, Roberto Pirrone, Edoardo Ardizzone
Detecting Sounds of Interest in Roads with Deep NetworksPasquale Foggia, Alessia Saggese, Nicola Strisciuglio, Mario Vento, Vincenzo Vigilante
On the Detection of GAN-based Face Morphs using Established Morph DetectorsLuca Debiasi, Naser Damer, Alexandra Mosegui Saladie, Christian Rathgeb, Ulrich Scherhag, Christoph Busch, Florian Kirchbuchner, Andreas Uhl
 
Poster 4 · 14:30 – 16:30
1Hand Gestures for the Human-Car Interaction: the Briareo DatasetFabio Manganaro, Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara
2Evaluation of Continuous Image Features Learned by ODE NetsFabio Carrara, Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro
3The Effects of Data Sources: a Baseline Evaluation of the MoCA DatasetElena Nicora, Gaurvi Goyal, Nicoletta Noceti, Francesca Odone
4Comparisons of Visual Activity Primitives for Voice Activity DetectionMuhammad Shahid, Cigdem Beyan, Vittorio Murino
5An UAV Autonomous Warehouse Inventorying by Deep LearningAntonio De Falco, Fabio Narducci, Alfredo Petrosino
6Weakly Supervised Semantic Segmentation Using Constrained Dominant SetsSinem Aslan, Marcello Pelillo
71-D DCT Domain Analysis for JPEG Double Compression DetectionOliver Giudice, Francesco Guarnera, Antonino Paratore, Sebastiano Battiato
8Contrastive Explanations to Classification Systems Using Sparse DictionariesAndrea Apicella, Francesco Isgro, Roberto Prevete, Gugliemo Tamburruni
9Segmentation of Pigment Signs in Fundus Images for Retinitis Pigmentosa Analysis by using Deep LearningDaniel Riccio, Maria Frucci, Nadia Brancati, Luigi Di Perna, Francesca Simonelli
10Automatic Creation of Large Scale Object Databases from Web Resources: a Case Study in Robot VisionDario Molinari, Giulia Pasquale, Lorenzo Natale, Barbara Caputo
11Dynamic Texture Classification Using Deterministic Partially Self-avoiding Walks on NetworksLucas C. Ribas, Odemir Bruno
12Vision Based Driver Smoking Behavior Detection Using Surveillance Camera ImagesYusuf Artan, Burak Balci, Bensu Alkan, Alperen Elihos
13Within-Network Ensemble for Face Attributes ClassificationSara Ahmed, Berrin Yanikoglu
14Memory Efficient Deployment of an OpticalFlow Algorithm on GPU using OpenMPOlfa Haggui, Claude Tadonki, Fatma Sayadi, Bouraoui Ouni
15Visual and Textual Sentiment Analysis of Daily News Social Media Images by Deep LearningAndrea Felicetti, Massimo Martini, Marina Paolanti, Roberto Pierdicca, Emanuele Frontoni, Primo Zingaretti
16Semantic Guided Deep Unsupervised Image SegmentationSudipan Saha, Swathikiran Sudhakaran, Biplab Banerjee, Sumedh D Pendurkar
17Using Handwriting Features to Characterize Cognitive ImpairmentNicole Dalia Cilia, Claudio De Stefano, Francesco Fontanella, Mario Molinara, Alessandra Scotto Di Freca
18Gaze-based Human-Robot Interaction by the Brunswick ModelRiccardo Berra, Francesco Setti, Marco Cristani
19ultiple Organs Segmentation in Abdomen CT Scans Using a Cascade of CNNsMuhammad Usman Akbar, Shahab Aslani; Vittorio Murino, Diego Sona
20Virtual Crowds: an LSTM-based Framework for Crowd SimulationNicola Garau, Niccolò Bisagno, Nicola Conci, Andrea Montagner
21Worldly Eyes on Video: Learnt vs. Reactive Deployment of Attention to Dynamic StimuliRaffaella Lanzarotti, Giuliano Grossi, Vittorio Cuculo, Alessandro D'Amelio
22Classification of Skin Lesions by Combining Multilevel Learnings in a DenseNet ArchitecturePierluigi Carcagni, Marco Leo, Andrea Cuna, Pier Luigi Mazzeo, Paolo Spagnolo, Giuseppe Celeste, Cosimo Distante

 

 Workshops 

W1

Monday
Full Day
Aula 1

International Workshop on Pattern Recognition for Cultural Heritage (PatReCH 2019)
Francesco Fontanella, Mario Molinara, Filippo Stanco
W2

Tuesday
09:00-13:00
Aula 1

DeepRetail: Deep Understanding of Shopper Behaviours and Interactions in Intelligent Retail Environment

Emanuele Frontoni, Sebastiano Battiato, Cosimo Distante, Marina Paolanti, Luigi di Stefano, Giovanni Maria Farinella, Anette Wolfrath, Primo Zingaretti

W3

Tuesday
09:00-13:00
Aula 3

BioFor Workshop on Recent Advances in Digital Security: Biometrics and Forensics
Daniel Riccio, Chang-Tsun Li, Francesco Marra, Diego Gragnaniello
W4

Tuesday
14:30-19:00
Aula 1

1st International Workshop on eHealth in the Big Data and Deep Learning Era
Tanmoy Chakraborty, Stefano Marrone, Giancarlo Sperlì

 Tutorials 

T1
Monday
09:00-11:00
Aula 2
Vision, Language and Action: from Captioning to Embodied AI
Lorenzo Baraldi, Marcella Cornia e Massimiliano Corsini
T2

Monday
09:00-11:00
Aula 3

Transferring Knowledge Across Domains: an Introduction to Deep Domain Adaptation
Massimiliano Mancini, Pietro Morerio

T3

Monday
11:30-13:00
Aula 3

Fingerprint Presentation Attacks Detection: lessons learned and a ROADMAP to the Future
Gian Luca Marcialis
T4

Monday
11:30-13:00
Aula 2

Probabilistic and deep learning for regression in computer vision
Xavier Alameda-Pineda, Stéphane Lathuilière
T5

Monday
14:30-16:30
Aula 2

Anomaly Detection in Images
Giacomo Boracchi, Diego Carrera
T6

Tuesday
14:30-16:30
Aula 3

High-Dynamic-Range imaging: improvements and limits
Alessandro Rizzi

 Special Sessions 

Industrial Session

In this Industrial Session, we will bring together researchers and practitioners in industrial engineering and computer science interested in industrial machine vision to overview the state of the art and identify the most interesting research lines.

The industrial session will host several companies as well as start-ups to show their activities while assessing them with respect to the cutting-edge research in the respective areas.

DAFNE Challenge

ICIAP2019 will host the presentation of the results of the DAFNE Challange (Digital Anastylosis of Frescoes challeNgE).

The DAFNE Challenge is an international competition in the artistic heritage sector designed to provide virtual solutions that ultimately add to the fresco restorer’s toolkit. The deadline for on-line registration is 31st May 2019.

Brave New Ideas

On Thursday, September 12th, ICIAP 2019 will host a special oral session with "brave new ideas" papers. These papers explore highly innovative ideas, visionary applications and theoretical paradigm shifts in the area of computer vision, pattern recognition, machine learning, multimedia analysis, and image processing.

These papers can arise, for instance, from highly interdisciplinary works (e.g. involving socio-technical studies), from research that exploits innovative data sources as well as from studies that adopt radically new strategies for addressing a well-established task. Due to their visionary nature, the underlying studies can be at an embryonic stage and experimental results can be at preliminary level. 

Ontology-Driven Food Category Classification in ImagesIvan Donadello, Mauro Dragoni
Image-to-Image Translation to Unfold the Reality of Artworks: an Empirical AnalysisMatteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Image Memorability using Diverse Visual Features and Soft AttentionMarco Leonardi, Luigi Celona, Paolo Napoletano, Simone Bianco, Raimondo Schettini, Franco Manessi, Alessandro Rozza
Automatic Creation of Large Scale Object Databases from Web Resources: a Case Study in Robot VisionDario Molinari, Giulia Pasquale, Lorenzo Natale, Barbara Caputo

CVPL Highlights

We invited the CVPL affiliated labs to present their CVPR 2019 and forthcoming ICCV papers during this special session of ICIAP 2019.
 
The CVPL Highlights will be presented on Friday 13th, during the following sessions.
Session 1 (Friday 13 September, 10:30-11:00)
Latent Space Autoregression for Novelty DetectionDavide Abati, Angelo Porrello, Simone Calderara, Rita Cucchiara
Model Vulnerability to Distributional Shifts over Image Transformation SetsRiccardo Volpi, Vittorio Murino
Fitting Multiple Heterogeneous Models by Multi-class Cascaded T-linkageLuca Magri, Andrea Fusiello
Domain Generalization by Solving Jigsaw PuzzlesFabio M. Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, Tatiana Tommasi
Real-time Self-adaptive Deep StereoAlessio Tonioni, Fabio Tosi, Matteo Poggi, Stefano Mattoccia, Luigi di Stefano
Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial LearningGianluca Agresti, Henrik Schaefer, Piergiorgio Sartor, Pietro Zanuttigh
AdaGraph: Unifying Predictive and Continuous Domain Adaptation through GraphsMassimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
 
Session 2  (Friday 13 September, 11:30-12:00)
Quasi-Unsupervised Color ConstancySimone Bianco, Claudio Cusano
View-LSTM: Novel-view Video Synthesis through View DecompositionMohamed Ilyes Lakhal, Oswald Lanz, Andrea Cavallaro
Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image TranslationMatteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Animating Arbitrary Objects via Deep Motion TransferAliaksandr Siarohin, Stephane Lathuiliere, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
Query-guided End-to-End Person SearchBharti Munjal, Sikandar Amin, Federico Tombari, Fabio Galasso
LSTA: Long Short-Term Attention for Egocentric Action RecognitionSwathikiran Sudhakaran, Sergio Escalera, Oswald Lanz
What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality AttentionAntonio Furnari, Giovanni Maria Farinella

 Presenter instructions 

OralIt consists of 12 minutes of presentation on stage + 3 minutes for questions. The presenters can bring their laptop on the stage.
Spotlight

It consists of 3:15 minutes of presentation + poster presentation. The slideshow will be a video that will be played, which should be 4:3 in MP4 format. Each presenter must upload the spotlight slideshow video by September 4, using this form. For the spotlight presentations, we require MP4 video of the slides with a resolution of 1920x1440p preferred. This will enable us to load all talks onto the same laptop without any configuration/format issues while allowing presenters to use whatever graphics/video tools they choose to generate the presentation.
You may upload your video at a different resolution, however, the projector’s native resolution is 1920×1440p, a 4:3 format. Videos that do not fit this resolution will be resized for the presentation.
Presentations must be limited to 3 minutes and 15 seconds, with the next video starting at 3 minutes and 20 seconds. The videos will be automatically played in order; there will be no presenter control and the next presentation will just start. If a video is longer than 3:15 it will be truncated. If a video is not in the proper format, it will be converted as best as our automated tool will do and probably of lower quality and could even be solid black or play incorrectly at the conference, so please follow these instructions carefully.
The session chairs will not be introducing each spotlight, therefore, please ensure the video starts with a title slide. When presenting introduce yourself. There will be no time allotted for questions after each spotlight. In addition to the spotlight presentation, please remember to prepare a poster for your paper which will be presented in the interactive session following your spotlight.
More details on video formatting.
For any questions, please contact mancini@fbk.eu.

Poster

It consists of a poster presentation on a panel of size 1.5m height × 1m width (A0 - portrait fits). Place your poster on the panel with the corresponding number (check the detailed program above).

CVPL Highlights

For the CVPL highlights, we require a file containing the slideshow, without any constraint on the format. This will enable us to load all talks on the same laptop. Each presenter must upload the highlight slideshow file by September 4, using this form. Presentations must be limited to 3 minutes and 15 seconds. The session chairs will not be introducing each highlight, therefore, please ensure your presentation starts with a title slide. When presenting introduce yourself. There will be no time allotted for questions after each presentation.
For any questions, please contact mancini@fbk.eu.

 

 Registration & Fees 

To participate in the conference, register by using the form available below.    Online registration is now closed, please register onsite!

Please note that the maximum number of participants is limited to 220.

Onsite registration may be offered on a space-available basis. Please contact the organizing committee ahead of the conference to make sure that you can register onsite, and note that onsite registration desks will close once the full capacity is reached. Please note that on-site registration payments can be processed only by credit cards or in cash.

Accompanying persons or IAPR members not attending the conference may attend the social dinner if there are still places available and pay directly at the restaurant.

Full Conference

The registration fee for the full conference participants covers:

  • admission to all conference sessions for 5 days
  • abstract book
  • conference kit
  • coffee breaks for 5 days
  • welcome reception
  • social dinner
Fees
Profile Early bird up to July 19Late fee July 20 - August 20Onsite * 

Regular

€ 700

€ 750

€ 800

IAPR member

€ 600

€ 650

€ 700

Student

€ 400€ 450€ 500
IAPR Student member

€ 350

€ 400€ 450

* only POS payment are accepted

Workshops/Tutorial/Industrial only

The registration fee for the Workshop/Tutorial/Industrial participants covers:

  • admission to all conference sessions for 2 days
  • abstract book
  • conference kit
  • coffee breaks for 2 days
  • welcome reception

Fees
Profile Early bird up to July 19Late fee July 20 - August 20Onsite * 

Regular

€ 350

€ 400

€ 450

IAPR member

€ 300€ 350€ 400

Student

€ 250€ 300€ 350

* only POS payment are accepted

VISA

If you need an invitation letter for a visa, you must register for ICIAP 2019 and pay the fee before we can issue an invitation letter.
International registrants should be particularly aware and careful about visa requirements and should plan travel well in advance. 

 Venue 

The event will be hosted at the Palazzo di Giurisprudenza.

Kindly notice, ICIAP participants will be welcommed at the Foyer, via Rosmini 27. 

Getting in

By Plane

The nearest airports to Trento are:
1. Verona Valerio Catullo, Italy (90 km);
2. Treviso A. Canova (135 km)
3. Venice Marco Polo, Italy (163 km);
4. Innsbruck, Austria (172 km)
5. Bergamo Orio al Serio, Italy (180 km)
6. Milano Linate and Malpensa, Italy (250 km)
7. Munich, Germany (312 km)

Verona Valerio Catullo Airport Verona-Trento by train takes about 1 hour. The closest airport to Trento is the International Airport of Verona Valerio Catullo.
The airport offers connections to the major European destinations, including the international hubs of Frankfurt, Paris, London Gatwick, and Rome, and some low-cost flights (RyanAir from Frankfurt and Bremen; Transavia from Amsterdam; Germanwings from Berlin, Bonn and London Stansted). For more information visit the airport website. From the Verona Catullo airport to Verona Porta Nuova Railway Station, an Aerobus service is available every day, every 20 minutes.
You can find the shuttle to the railway station just outside the arrivals terminal of the Verona airport. You can buy the ticket online, directly on the bus or inside the airport in a ticket booth. The cost of a one-way ticket is 6 EUR.
The bus is available from 6:35 AM to 9:10 PM, every 20 minutes; from 20:10 to 11:30 every 40 minutes. The trip from the airport to the train station is around 15 minutes. For prices and timetables for the Verona-Trento train, please visit the site Trenitalia.

Treviso A. Canova The international airport A. Canova can be considered to reach Trento. Treviso-Trento by train takes about 3 hours. Treviso international A. Canova Airport is connected by a bus and taxi service to the nearby Treviso and Venezia Mestre railway stations: Locations served by bus from Treviso Antonio Canova Airport • Treviso: ACTT Line 6 • Venice railway station and Piazzale Roma: ATVO line.
The bus can be caught from the airport: in Via Noalese, to the right of the airport exit. Tickets can be bought at the ticket office in the Arrivals hall on the ground floor of Treviso Airport terminal building or on the bus. Connections between Treviso Canova international Airport and the Treviso and Venezia Mestre railway stations • Treviso station • ACTT Line 6 Journey time: 15-20 minutes
A bus can be caught from the airport: in Via Noalese, to the right of the airport exit. For more info please visit. http://www.trevisoairport.it/en/transport/train.html

Venice Marco Polo Airport. Venice-Trento by train takes about 2.5 hours
The International Airport of Venice Marco Polo can be considered to reach Trento. The Venice airport is well connected to the railway station of Venice-Mestre and Venice-Santa Lucia by ATVO and ATCV buses. Venice-Mestre railway station is reachable by bus no 15, Venice-Santa Lucia railway station is reachable by bus no 5.
Please, note that if you consider Venice-Santa Lucia railway station you have to get off the bus in Piazzale Roma and from there walk 10 minutes over the bridge Ponte della Costituzione. You can buy the ticket from a ticket booth or online before your arrival. The cost of a one-way ticket is 8 EUR.
The bus line is available from 6 AM to 12:00 PM. The trip from the airport to the train stations is around 35 minutes. For prices and timetables for the Venice-Trento train, please visit the site of Trenitalia.

Innsbruck Airport. Innsbruck-Trento by train takes about 2.5 hours The International Airport of Innsbruck (Austria) can be considered to reach Trento. The Innsbruck main train station is easily accessed by train or bus from the Innsbruck Airport. Bus route F connects the Innsbruck main station with the airport main building. The journey takes about 20 minutes.
For prices and timetables for the Innsbruck-Trento train, please visit the site of Austrian railways.

Bergamo Orio al Serio Airport. Bergamo-Trento by train takes about 3.5 hours.
The International Airport of Bergamo Orio al Serio is a basis for many low-cost flights (e.g., RyanAir from London Stansted, Paris Beauvais, Barcelona Girona, Valencia). The Bergamo railway station is easily reachable by ATB shuttle bus from the airport in only 15 minutes You can buy the ticket either from a newspaper kiosk or from a ticket booth. The cost of a one-way ticket is 2 EUR.
The bus line is available from 6:15 AM to 12:00 PM, every 20 minutes. The trip from the airport to the train station is around 15 minutes. For prices and timetables for the Bergamo-Trento train, please visit the site of Trenitalia.

Milano Linate Airport. Milano-Trento by train takes about 3 hours.
The airport of Milano Linate can be considered to reach Trento. Milano Linate is just 7 km from the Milano city centre and can be easily reached with various airport shuttles and with ATM lines 73 Urban line 73 Milan Piazza San Babila M1 - Linate First departure: 5:35 a.m. Last departure: 12:35 a.m. Departures every 10 minutes, every day Fare: 1,5 euro Company: ATM www.atm.it
Further info on: http://www.milanolinate-airport.com/en/directions-and-parking/by-bus
Also, a taxi can be considered.
For prices and timetables for the Milano-Trento train please, visit the site of Trenitalia.

Milano Malpensa Airport Milano-Trento by train takes about 3 hours.
The International Airport of Milano Malpensa can be considered to reach Trento. From Malpensa airport take the Malpensa Express train to Milano, Stazione Nord. Once there, take subway line 2 (green line) to reach the Central Train Station. For prices and timetables for the Milano-Trento train, please visit the site of Trenitalia.

Munich Airport. Munich-Trento by train takes about 4.5 hours.
The International Airport of Munich (Germany) can be considered to reach Trento. Trento can be directly reached by train from Munich: for the train schedule, please visit the site of the German State railways. By train Train tickets can be purchased at the railway station. Italian train tickets must be stamped with the yellow machines available at the platform (binario) entrance before getting on the train. In buying your ticket you should specify the arrival station (Trento), the train you are planning to take (some InterCity trains require a supplement that is more expensive if purchased on the train) and the class: 1st (prima) or 2nd (seconda). First class is more comfortable and about 60% more expensive.
Find trains and purchase tickets online • Trenitalia (Italian State Railways) • Deutsche Bahn (German State Railways) • Obb (Austrian State Railways) • Sbb (Swiss State Railways)

By Car

If you are reaching Trento from the north, exit the A22 motorway at TRENTO NORD and follow the signs to go to the Trento city center. If you are reaching Trento from the south, exit the A22 motorway at TRENTO SUD and follow the signs to go to the Trento city center. ViaMichelin is a good link for getting detailed driving directions. Please note that trip advisors may still suggest: TRENTO CENTRO as A22 motorway, but this is closed.

By Train

You can reach Trento by train from almost everywhere in Europe. The main companies which travel to Trento are:

OBB http://www.oebb.at/en/

BAHN https://www.bahn.com/

TRENITALIA http://www.trenitalia.com/

About the City

The city of Trento: the unique charm of a renaissance alpine city, where history is art.

Trento is a city rooted in art and history, where the Italian and Mitteleuropean cultures meet. Unique amongst the alpine cities, the City of the Council (1545 - 1563) still keeps its precious monuments as tokens of its rich artistic and historic heritage. Built in the elegant renaissance style, they have been enhanced by recent refurbishing works.

Special mention goes to the Castello del Buonconsiglio, the Castle for several centuries residence of the Prince-Bishops of Trento; the Duomo, the Cathedral of Trento dedicated to San Vigilio, its gorgeous piazza and fountain dedicated to Neptune, the frescoed houses and Council churches as well as the museums and exhibitions which make the city of Trento a true landmark of alpine arts, culture and traditions.

Concilio di Trento (Concilium Tridentinum)

The Council of Trento, held between 1545 and 1563 in Trento and Bologna, was one of the Roman Catholic Church’s most important ecumenical councils. Prompted by the Protestant Reformation, it has been described as the embodiment of the Counter-Reformation.

Castello del Buonconsiglio (Buonconsiglio Castle)

The Castello del Buonconsiglio is the largest and most important monumental complex of the Trentino Alto Adige region.

It was the residence of the Principi Vescovi (Prince-Bishops) of Trentofrom the 13th century to the end of the 18th century, and is composed of a series of buildings of different eras, enclosed by walls and positioned slightly higher than the city:

  • the Castelvecchio is the oldest part, dominated by an imposing cylindrical tower
  • the Magno Palazzo is the 16th century expansion in the Italian Renaissance-style as commissioned by the Prince-Bishop and Cardinal Bernardo Clesio (1485-1539)
  • the Baroque-style Giunta Albertiana dates from the end of the 17thcentury
  • at the extreme south of the complex is the Torre Aquila, within which is conserved the famous Cycle of the Months, one of the most fascinating secular pictorial cycles of the late Middle Ages.

Also of exceptional interest are the extensive cycle of frescoes commissioned by the bishops to decorate the interior walls of the Castle, mainly in the late Middle Ages to the Renaissance period. After the end of the Episcopal principality (1803) the castle was used as a barracks; following its restoration in 1924, it became the National Museum, and since 1973 it belongs to the Autonomous Province of Trento.

Duomo di Trento (Cathedral of Trento)

Trento’s Cathedral is dedicated to Saint Vigil and has ancient origins.

There are in fact records that indicate the first church was built on the burial ground of this saint, martyred in the fifth century. It was then enlarged, whilst its present appearance is owed to Bishop Federico Vanga, who entrusted the redesigning of the cathedral to Adam d’Argogno in 1212. The position of the church is the result of his plan.

The construction, continued over the centuries by d’Arogno’s descendants, underwent various changes with respect to the original project due both to the churches needs and the changes in construction techniques. The contrast between the Romanesque style and the height of the vaults recalling gothic cathedrals is extraordinary. Two climbing staircases built into the lateral walls lead up to the two bell towers, in the opposite direction to the altar. Amongst the numerous works of art it is worth noting the worshipped wooden statue of Our Lady of Sorrow, some of the altars, a series of canvasses, the Romanesque sculpture (credited to Adam d’Arogno) called the Madonna of the Drowned, at whose feet the bodies of people who drowned in the Adige or the irrigation channels that flowed through the city and funeral monuments of numerous famous political and religious characters were placed.

In the southern aisle the Alberti Chapel can be found. This contains a large crucifix, in front of which, on 4 December 1563 at the end of the Council, the decrees of the counterreformation were promulgated.

The high Altar with a baroque canopy above, erected in the middle of the eighteenth century with the annulment of the citizens vote during the French siege of 1703, holds the urn with the relics of Saint Vigil.

The frescoes, created between the 13th and 15th century, can be attributed to painters from Venetian, Lombardian and late gothic schools and depict classic Christian themes.

The palaeochristian basilica can be entered from the northern transept, which an excavation campaign lasted several years made accessible.

Trento offers visitors its richly historical and artistic heritage all year around. Visitors can admire its beauties while strolling around the city centre’s alleys, enjoying shopping or visiting the city’s museums.

Museo del Castello del Buonconsiglio

The castle has numerous art and archaeological collections that were first assembled in the mid-19th century within the Civic Museum of Trento and include objects that date from prehistory up to the first half of the 19thcentury documenting the historical and artistic events of Trento and its surrounding territory.

For more information, please see the dedicated website.

MUSE, Museo delle Scienze (MUSE, Science Museum)

MUSE is a place of constant change, from the main exhibitions, up to date with the latest developments, to special projects, with prestigious national and international collaborations, and finally to MUSE Lab, where the most advanced experiments in the field of new technologies take place.

The exhibition of Muse uses the metaphor of the mountain to describe life on Earth.

You start from the top: the terrace and the 4th floor allow us to encounter the sun and ice, and from there you descend to investigate the issues of biodiversity, sustainability, and evolution, until you reach the basement and the wonder of the tropical greenhouse.

Accomodations

Trento has special agreements with local Hotels and B&B to grant keen rates to the Congress' participants. Please find in the enclosed lists 2018 fees. Please notice that the mentioned rates can be granted according to the availability and only with personally contacting the hotel for booking.

Hotel rates offered to the University of Trento

Social Events

Reception at the Buonconsiglio Castle

The Buonconsiglio Castle is a museum as well as the largest monumental complex in Trentino-Alto Adige. The Castle built up against the 13th-century city walls served as the residence of the Bishops of Trento from the second half of the 13th century until the secularization of the principality in 1803 and is composed of a series of buildings of different eras, enclosed by walls and positioned slightly higher than the city.

Today it is the seat of the Museo Provinciale d'Arte (Provincial Art Museum), monuments and provincial art collections. It holds numerous collections of art, paintings, sculptures, graphic works, miniate codes, majolica ovens, as well as archaeological and numismatic collections. Among its many Baroque and Gothic frescoes, an outstanding work is the Ciclo dei Mesi (Cycle of the Months) considered one of the most significant examples of international Gothic style in the world.

The Castle is located in the very center of Trento at a walking distance from the Conference venue.

Castello del Buonconsiglio
Via Bernardo Clesio, 5
Trento - Italia
www.buonconsiglio.it

Credits: Carmen Buffa (Archivio UniTrento)

Banquet at Villa Bortolazzi

Located a short distance from the village of Mattarello, Villa Bortolazzi at Acquaviva will allow visitors to appreciate the evocative eighteenth-century atmospheres enclosed within a building with simple and linear contours built in 1693 by Comacini Apollonio and Pietro Somalvico. Adorned by the vast park, the avenue that runs between two boxwood hedges and a garden decorated with statues of divinities and allegories in silent conversation, the exterior of the villa restores a fascinating Arcadian atmosphere. Once through the threshold, the route will allow you to admire the frescoed 18th-century pictorial decoration, the exuberant stucco cornices and the dizzying architectural partitions made by the Trentine painter Antonio Gresta and the Modenese Domenico Romani. The halls of the villa are frescoed with mythological, allegorical scenes, heraldic compositions, elaborate eighteenth-century perspective architectures among which we remember the central hall with the Apotheosis of the Sun between the figures of the Seasons, of the wife Neera and of the two daughters who feed the horses of the chariot of the sun made by Antonio Gresta. The delightful Chapel dedicated to the Blessed Virgin Mary of Carmel is enhanced by paintings by G. B. Cignaroli and by the altar attributed to Giuseppe Antonio Sartori.

Villa Bortolazzi is located in Mattarello, a small village at 20 minutes of distance from the Conference venue. There will be buses from and to the conference venue.

Villa Bortolazzi
Località Acquaviva, 10
38123, Mattarello di Trento, TN
http://www.villabortolazzi.it/

AcquaViva  

 Committees 

General Chairs
  • Oswald Lanz, Fondazione Bruno Kessler
  • Stefano Messelodi, Fondazione Bruno Kessler
  • Nicu Sebe, University of Trento
Program Chairs
  • Elisa Ricci, University of Trento & Fondazione Bruno Kessler
  • Samuel Rota-Bulò, Mapillary Research
  • Cees Snoek, University of Amsterdam
Workshop Chairs
  • Marco Cristani, University of Verona
  • Andrea Prati, University of Parma
Tutorial Chairs
  • Costantino Grana, University of Modena e Reggio Emilia
  • Lamberto Ballan, University of Padova
Special Session Chairs
  • Marco Bertini, University of Florence
  • Tatiana Tommasi, Italian Institute of Technology
Industrial Chairs
  • Paul Chippendale, Fondazione Bruno Kessler
  • Fabio Galasso, OSRAM
Publicity/Web Chairs
  • Davide Boscaini, Fondazione Bruno Kessler
  • Massimiliano Mancini, Sapienza University of Rome, Fondazione Bruno Kessler & Italian Institute of Technology
Publication Chair
  • Michela Lecca, Fondazione Bruno Kessler
Local Chairs
  • Fabio Poiesi, Fondazione Bruno Kessler
  • Gloria Zen, University of Trento
  • Stéphane Lathuillère, University of Trento
Asia Liaison Chair
  • Ramanathan Subramanian, University of Glasgow, Singapore
USA Liaison Chair
  • Yan Yan, Texas State University, USA

Steering Committee

Virginio Cantoni, University of Pavia

Luigi Pietro Cordella, University of Napoli Federico II

Rita Cucchiara, University of Modena and Reggio Emilia

Alberto Del Bimbo, University of Firenze

Marco Ferretti, University of Pavia

Gian Luca Foresti, University of Udine

Fabio Roli, University of Cagliari

Gabriella Sanniti di Baja, ICAR-CNR

Area Chairs

Video Analysis and Understanding

Andrea Cavallaro, Queen Mary University of London

Efstratios Gavves, University of Amsterdam


Pattern Recognition & Machine Learning

Battista Biggio, University of Cagliari

Marcello Pelillo, University of Venice


Deep Learning

Marco Gori, University of Siena

Francesco Orabona, Boston University


Multiview Geometry and 3D Computer Vision

Andrea Fusiello, University of Udine

Alessio Del Bue, Istituto Italiano di Tecnologia (IIT), Genova

Federico Tombari, Technische Universität München


Image Analysis, Detection and Recognition

Barbara Caputo, University of Rome, La Sapienza

Jasper Uijlings, Google AI


Multimedia

Xavier Alameda-Pineda, INRIA

Francesco De Natale, University of Trento


Biomedical and Assistive Technology

Giovanni Maria Farinella, University of Catania

Roberto Manduchi, UCSC


Digital Forensics

Giulia Boato, University of Trento

Fernando Pérez-González, University of Vigo


Image processing for Cultural Heritage

Andreas Rauber, TU Wien

Lorenzo Seidenari, University of Florence


Brave New Ideas

Michele Merler, IBM T. J. Watson Research Center

Concetto Spampinato, University of Catania

 Download 

Invoice Data PA (DOC | 0.1MB )