Main Conference Program

 

Schedule

REGISTRATION OPENING - Sept 9 at 8:00 - sept 10 and 11 AT 8:30

Wednesday 9 Sept. 2015 

  8:45 - 9:00   Welcome   
  9:00 - 9.50   Invited Talk 1 A. Smeulders - "Visual cognition"
  9:50 - 11.20   Poster Session 1 Pattern Recognition & Machine Learning
  11:00 - 11:30   Coffee Break  
  11:30 - 13.10   Oral Session 1 Pattern Recognition & Machine Learning
  13:10 - 14.30   Lunch  
  14:30 - 16.00   Poster Session 2 Image Analysis 1
  15:45 - 16:15   Coffee Break  
  16:15 - 17.05   Invited Talk 2 M. Irani - "Blind Optics"
  17:05 - 18.05   Oral Session 2 Image Analysis 1
         
  18.15 GIRPR meeting
         
  20:15   Welcome Cocktail  
         

 Thursday 10 Sept. 2015

  9:00 - 9.50   Invited Talk 3 B. Schiele - "Towards Visual Scene Understanding - It's Time to Address it Again"
  9:50 - 11.20   Poster Session 3 Image Analysis 2
  11:00 - 11:30   Coffee Break  
  11:30 - 13:10   Oral Session 3 Image Analysis 2
  13:10 - 14.30   Lunch  
  14:30 - 16.00   Poster Session 4 Shape Analysis & 3D Computer Vision
  15:45 - 16:15   Coffee Break  
  16:15 - 17.05   Invited Talk 4 K. Grauman - "Searching and Browsing Visual Data"
  17:05 - 18.45   Oral Session 4 Shape Analysis & 3D Computer Vision
         
  20:00   Social Dinner  
         

 Friday 11 Sept. 2015

  9:00 - 9.50   Invited Talk 5 X. Wang - "DeepID: Deep Learning for Face Recognition"
  9:50 - 11.20   Poster Session 5 Biomedical Applications & Video Analysis
  11:00 - 11:30   Coffee Break  
  11:30 - 13:10   Oral Session 5 Biomedical Applications
  13:10 - 14.30   Lunch  
  14:30 - 15.20   Invited Talk 6 S. Bengio - "The Battle Against the Long Tail in Computer Vision"
  15:20 - 16.45   Oral Session 6 Video Analysis & Multimedia
         
  16.45 Closing

 

ORAL SESSIONS

Oral session 1: Pattern Recognition & Machine Learning

    Transfer Learning through Greedy Subset Selection
    Ilja Kuzborskij, Francesco Orabona, Barbara Caputo
   
    MEG: Multi-Expert Gender recognition in a demographics-balanced dataset
    Modesto Castrillon-Santana, Maria De Marsico, Michele Nappi, Daniel Riccio
   
    An Edge-based Matching Kernel through Discrete-time Quantum Walks
    Lu Bai, Zhihong Zhang, Peng Ren, Luca Rossi, Edwin Hancock
   
    Implicit Boundary Learning for Connectomics
    Tobias Maier, Thomas Vetter
   
    A Parzen-based distance between probability measures as an alternative of summary statistics in Approximate Bayesian Computation
     Carlos D. Zuluaga, Edgar A. Valencia, Mauricio A. Alvarez, Alvaro A. Orozco

 

Oral session 2: Image Analysis 1

    Learning Balanced Trees for Large Scale Image Classification
    Tien-Dung Mai, Thanh Duc Ngo, Duy-Dinh Le, Duc Anh Duong, Kiem Hoang, Shin'ichi Satoh
   
    Analysis of compact features for RGB-D visual search
    Alioscia Petrelli, Danilo Pau, Luigi Di Stefano
   
    Hierarchical image segmentation relying on a likelihood ratio test
    Silvio Jamil Guimaraes, Zenilton Kleber do Patrocinio Jr, Yukiko Kenmochi, Jean Cousty, Laurent Najman

 

Oral session 3: Image Analysis 2 

    Large Scale Specific Object Recognition by using GIFTS Image Feature 
    Hiroki Nakano, Yumi Mori, Chiaki Morita, Shingo Nagai
   
    On Tensor Product Spatiochromatic Features in Natural Images Statistics
    Edoardo Provenzi, Julie Delon, Yann Gousseau, Baptiste Mazin
   
    Real-time foreground segmentation with Kinect sensor
    Luigi Cinque, Alessandro Danani, Piercarlo Dondi, Luca Lombardi
   
    Hierarchical Image Representation Using Deep Network
    Emrah Ergul, Sarp Erturk, Nafiz Arica
   
    Fast Image Classification with Reduced Multiclass Support Vector Machines
     Marco Melis, Luca Piras, Battista Biggio, Giorgio Giacinto, Giorgio Fumera, Fabio Roli

 

Oral session 4: Shape Analysis & 3D Computer Vision

    Fuzzy “Along” Spatial Relation in 3D. Application to Anatomical Structures in Maxillofacial CBCT
    Timothée Evain, Xavier Ripoche, Jamal Atif, Isabelle Block
   
    Fast and Precise Geodesic Distances On Manifold Surfaces
    Rosario Aiello, Francesco Banterle, Nico Pietroni, Luigi Malomo, Paolo Cignoni, Roberto Scopigno
   
    Comparing persistence diagrams through complex vectors
    Barbara Di Fabio, Massimo Ferri
   
    Pop-up Modelling of Hazy Scenes
    Lingyun Zhao, Miles Hansard, Andrea Cavallaro
   
    3D Geometric Analysis of Tubular Objects based on Surface Normal Accumulation
     Bertrand Kerautret, Adrien Krähenbühl, Isabelle Debled-Rennesson, Jacques-Olivier Lachaud

 

Oral session 5: Biomedical Applications

    Efficient Resolution Enhancement Algorithm for Compressive Sensing Magnetic Resonance Image Reconstruction
    Osama Omer, Mohamed A. Bassiouny, Ken'ichi Morooka
   
    Towards accurate segmentation of fibroglandular tissue in breast MRI using fuzzy c-means and skin-folds removal
    Mohammad Razavi, Lei Wang, Albert Gubern-Merida, Tatyana Ivanovska, Hendrik Laue, Nico Karssemeijer, Horst Hahn
   
    Robust and Fast Vessel Segmentation via Gaussian Derivatives in Orientation Scores
    Jiong Zhang, Erik Bekkers, Samaneh Abbasi, Behdad Dashtbozorg, Bart ter Haar Romeny
   
    Information-based cost function for the Bayesian MRI segmentation framework
    David Cárdenas-Peña, Alvaro A. Orozco, Germán Castellanos-Dominguez
   
    Learning by Sampling for White Blood Cells Segmentation
     Cecilia Di Ruberto, Andrea Loddo, Lorenzo Putzu

 

Oral session 6: Video Analysis & Multimedia

    Automated Recognition of Social Behavior in Rats: The Role of Feature Quality
    Malte Lorbach, Ronald Poppe, Elsbeth van Dam, Lucas Noldus, Remco Veltkamp
   
    Scale and Occlusion Invariant Tracking-by-Detection
    Andrea Mazzeschi, Giuseppe Lisanti, Federico Pernici, Alberto Del Bimbo
   
    Ensemble of Hankel Matrices for Face Emotion Recognition
    Liliana Lo Presti, Marco La Cascia
   
    Emotions in Abstract Art: Does Texture Matter?
    Andreza Sartori, Berhan Şenyazar, Alkim Almila Akdag Salah, Albert Ali Salah, Nicu Sebe

 

 

POSTER SESSIONS 

Multi-Resolution Indexing spystealth.com and Retrieval Method of Time Series Using Discrete Wavelet Transform 

Poster session 1: Pattern Recognition & Machine learning

 
 
Fitting Multiple Models via Density Analysis in Tanimoto Space
Luca Magri, Andrea Fusiello
 
Bag Of Graphs with Geometric Relationships among Trajectories for Better Human Action Recognition
Manel Sekma, Mahmoud Mejdoub, Chokri Benamar
 
Have a SNAK. Encoding spatial information with the Spatial Non-Alignment Kernel
Radu Tudor Ionescu, Marius Popescu
 
Convolved multi-output Gaussian processes for Semi-Supervised Learning
 Hernan Dario Vargas Cardona, Mauricio A. Alvarez, Alvaro A. Orozco
 
Volcano-seismic events classification using document classification strategies
Manuele Bicego, John Makario Londoño-Bonilla, and Mauricio Orozco-Alzate
 
Unsupervised Feature Selection by Graph Optimization
Zhihong Zhang, Lu Bai, Yuanheng Liang, Edwin Hancock
 
Gait Recognition Robust to Speed Transition using Mutual Subspace Method
Yumi Iwashita, Hitoshi Sakano, Ryo Kurazume
 
Path-Based Dominant-Set Clustering
 Eyasu Zemene, Marcello Pelillo
 
Global and Local Gaussian Process for Multioutput and Treed Data
Jhouben J. Cuesta, Mauricio A. Alvarez, Alvaro A. Orozco
 
BRISK local descriptors for heavily occluded ball recognition
Pier Luigi Mazzeo, Paolo Spagnolo, Cosimo Distante
 
Neighborhood Selection for Dimensionality Reduction
Paola Campadelli, Elena Casiraghi, Claudio Ceruti
 
Crowdsearching Training Sets for Image Classification
Sami Abduljalil Abdulhak, Walter Riviera, Marco Cristani
 
The color of smiling: computational synaesthesia of facial expressions
Vittorio Cuculo, Raffaella Lanzarotti, Giuseppe Boccignone
 
 
Learning Texture Image Prior For Super Resolution Using Convolutional Neural Network
Chulmoo Kang, Minui Hong, Suk I. Yoo
 
GRUNTS: Graph Representation for UNsupervised Temporal Segmentation
Francesco Battistone, Alfredo Petrosino, Gabriella Sanniti di Baja
 
3DPyranet: A Strict Pyramidal Deep Neural Network
Ihsan Ullah, Alfredo Petrosino
 
Nerve localization by machine learning framework with new feature selection algorithm
Oussama Hadjerci, Adel Hafiane, Pascal Makris, Donatello Conte, Pierre Vieyres, Aain Delbos
 
Human tracking using a top-down and knowledge based approach
Benoit Gaüzère, Pierluigi Ritrovato, Alessia Saggese, Mario Vento

 

Poster session 2: Image Analysis 1 

A Gravitational Model for Plant Classification Using Adaxial Epidermis Texture
André Ricardo Backes, Jarbas Joaci de Mesquita Sá Junior, Rosana Marta Kolb 
 
Adaptive Background Modeling for Land and Water Composition Scenes
Jing Zhao, Shaoning Pang, Bruce Hartill, AbdolHossein Sarrafzadeh
   
Enhancing signal discontinuities with Shearlets: an application to corner detection
Miguel Alejandro Duval Poo, Francesca Odone, Ernesto De Vito 
   
Improved Human Gait Recognition
 Imad Rida, Ahmed Bouridane, Gian Luca Marcialis, Pierluigi Tuveri
   
Human Area Refinement of Human Detection
Rong Xu, Satoshi Ueno, Tatsuya Kobayashi, Naoya Makibuchi, Sei Naito
   
Skeletonization Algorithm using Discrete Contour Map
Hassan Id Ben Idder, Nabil Laachfoubi 
   
Superpixel and entropy-based multi-atlas fusion framework for the segmentation of X-ray images
Dac Cong Tai Nguyen, Said Benameur, Max Mignotte, Frédéric Lavoie 
   
Wavelet-like lifting-based transform for decomposing images in accordance with the inter-prediction principles of video coding
Marek Parfieniuk
   
 
   
Bounded Non-Local Means for Fast and Effective Image Denoising
Federico Tombari, Luigi Di Stefano 
 
i-Street: Detection, Identification, Augmentation of Street Plates in a Touristic Mobile Application
Stefano Messelodi, Carla Maria Modena, Lorenzo Porzi, Paul Chippendale 
   
Distortion Adaptive Descriptors: Extending Gradient-Based Descriptors to Wide Angle Images
Antonino Furnari, Giovanni Maria Farinella, Arcangelo Ranieri Bruna, Sebastiano Battiato 
   
Counting Turkish Coins with a Calibrated Camera
Burak Benligiray, Halil Ibrahim Cakir, Cihan Topal, Cuneyt Akinlar 
   
Design and Implementation of a Dynamic Adaptive Video Streaming System with a Buffer Aware Rate Selection Algorithm
Venkata Phani Kumar M, Ravi K C, Sudipta Udipta Mahapatra 
   
Leveraging mutual information in local descriptions: from Local Binary Patterns to the image
Tahir Q. Syed, Sadaf I. Behlim, Alishan K. Merchant, Alexis Thomas, Furgan M. Khan 
   
Dominant LBP Considering Pattern Type for Facial Image Representation
Alaa Sagheer, Shimaa Saad 
   
Improving high resolution satellite images retrieval using color component features
Houria Sebai, Assia Kourgli 
 
The QCRI Recognition System for Handwritten Arabic
Felix Stahlberg, Stephan Vogel 
   
Optimized Parallel Model of Covariance Based Person Detection
Nesrine Abid, Kais Loukil, Walid Ayedi, Ahmed Chiheb Ammari, Mohamed Abid 
   
Face recognition from robust SIFT matching
Massimiliano Di Mella, Francesco Isgrò 
   
Optimized Intra Mode Decision for High Efficiency Video Coding
Anis BenHajyoussef, Tahar Ezzedine 
 
Towards Learning free Naive Bayes Nearest Neighbor-based Domain Adaptation
Faraz Saeedan, Barbara Caputo 

 

Poster session 3: Image Analysis 2

A gravitational model for grayscale texture classification applied to the pap-smear database
Jarbas Joaci de Mesquita Sá Junior, André Ricardo Backes
 
Combining ARF and OR-PCA for Robust Background Subtraction of Noisy Videos
Sajid  Javed, Thierry Bouwmans, Soon Ki Jung
 
Image clarification method based on structure-texture decomposition with texture refinement
Masato Toda, Kenta Senzaki, Masato Tsukada
 
Detecting and tracking the tips of fluorescently labeled mitochondria in U2OS cells
Eero Lihavainen, Jarno Mäkelä, Johannes N. Spelbrink, Andre S. Ribeiro
 
Recognition of the human fatigue based on the ICAAM algorithm
Konrad Rodzik, Dariusz Sawicki
 
Rich QR code for multimedia management applications
Iuliia Tkachenko, William Puech, Olivier Strauss, Christophe Destruel, Jean-Marc Gaudin, Christian Guichard
 
Panel Tracking for the Extraction and the Classification of Speech Balloons
Hadi S. Jomaa, Mariette Awad, Lina Ghaibeh
 
Combining Hardwaremetry and Biometry for Human Authentication via Smartphones
Chiara Galdi, Michele Nappi, Jean-Luc Dugelay
 
Multi-scale opening-a new morphological operator
Subhadip Basu, Eric Hoffman, Punam K. Saha
 
Level-by-level Adaptive Disparity Compensated Prediction in Wavelet Domain for Stereo Image Coding
Shigao Li, Liming Jia
 
Logo Recognition Using CNN Features
Simone Bianco, Marco Buzzelli, Davide Mazzini, Raimondo Schettini
 
Person re-identification using robust brightness transfer functions based on multiple detections
Amran Bhuiyan, Behzad Mirmahboub, Alessandro Perina, Vittorio Murino
 
Analysis of HOG suitability for Facial Traits description in FER problems
Marco Del Coco, Pierluigi Carcagnì, Giuseppe Palestra, Marco Leo, Cosimo Distante
 
Difference-based Local Gradient Patterns for Image Representation
Alaa Sagheer, Shimaa Saad
 
Non-Local Sigma Filter
Nikolay Ponomarenko, Vladimir Lukin, Jaakko Astola, Karen Egiazarian
 
A New Multi-resolution Affine Invariant Planar Contour Descriptor
Taha Faidi, Faten Chaieb, Faouzi Ghorbel
A Light-weight Intra Prediction Mode Decision Algorithm for HEVC
 
Image Manipulation on Facebook for Forensics Evidence
Marco Moltisanti, Antonino Paratore, Sebastiano Battiato, Luigi Saravo
 
Improved Performance in Facial Expression Recognition Using 32 Geometric Features
Giuseppe Palestra, Adriana Pettinicchio, Marco Del Coco, Pierluigi Carcagnì, Marco Leo, Cosimo Distante
 
A Selection module for large-scale face recognition systems
Giuliano Grossi, Raffaella Lanzarotti, Jianyi Lin
 
A classification-selection approach for self updating of face verification systems under stringent storage and computational requirements
Pierluigi Tuveri, Valerio Mura, Gian Luca Marcialis, Fabio Roli
 
Super-Sparse Regression for Fast Age Estimation From Faces at Test Time

Ambra Demontis, Battista Biggio, Giorgio Fumera, Fabio Roli

Real-Time Age Estimation from Face Imagery using Fisher Vectors

Lorenzo Seidenari, Alessandro Rozza, Alberto Del Bimbo

 Unsupervised Classification of Raw Full-Waveform Airborne Lidar Data by Self Organizing Maps

 Eleonora Maset, Roberto Carniel, Fabio Crosilla

 

Poster session 4: Shape Analysis, 3D Computer Vision & Multimedia

Tongue in Cheek
George Nagy, Naomi Nagy
 
Where is the ground? Quality measures for the planar digital terrain model in Terrestrial Laser Scanning
Marcin Bator, Leszek J. Chmielewski, Arkadiusz Orłowski
 
Extending the sGLOH descriptor
Fabio Bellavia, Carlo Colombo
 
Fast Superpixel-based Hierarchical Approach to Image Segmentation
Francesco Verdoja, Marco Grangetto
 
Supertetras: a Superpixel Analog for Tetrahedral Mesh Oversegmentation
Giulia Picciau, Patricio Simari, Federico Iuricich, Leila De Floriani
 
Extraction of Successive Patterns in Document Images by a new Concept based on Force Histogram and Thick Discrete Lines
Isabelle Debled-Rennesson, Laurent Wendling
 
Hierarchical mesh segmentation editing through rotation operations
Federico Iuricich, Patricio Simari
 
Local feature extraction in log-polar images
Manuela Chessa, Fabio Solari
 
Scale-space Techniques for Fiducial Points Extraction from 3D Faces
Nikolas De Giorgis, Luigi Rocca, Enrico Puppo
 
Filtering Non-Significant Quench Points using Collision Impact in Grassfire Propagation
Dakai Jin, Cheng Chen, Punam K. Saha
 
Robust and Efficient Camera Motion Synchronization via Matrix Decomposition
Federica Arrigoni, Beatrice Rossi, Andrea Fusiello
 
Novel View-Synthesis from Multiple Sources for Conversion to 3DS
Francesco Malapelle, Andrea Fusiello, Beatrice Rossi, Pasqualina Fragneto
 
Dynamic Optimal Path Selection for 3D Triangulation with Multiple Cameras
Mara Pistellato, Filippo Bergamasco, Andrea Albarelli, Andrea Torsello
 
Smartphone-based Obstacle Detection for the Visually Impaired
Alessandro Caldini, Marco Fanfani, Carlo Colombo
 
Efficient moving point handling for incremental 3D manifold reconstruction
Andrea Romanoni, Matteo Matteucci
 
Volumetric 3D Reconstruction and Parametric Shape Modeling from RGB-D Sequences
Yoichi Nakaguro, Waqar Shahid Qureshi, Matthew N. Dailey, Mongkol Ekpanyapong, Pished Bunnun, Kanokvate Tungpimolrut
 
Movie Genre Classification by Exploiting MEG Brain Signals
Pouya Ghaemmaghami, Mojtaba Khomami Abadi, Seyed Mostafa Kia, Paolo Avesani, Nicu Sebe
 
Egocentric Video Personalization in Cultural Experiences Scenarios
Patrizia Varini, Giuseppe Serra, Rita Cucchiara
 
Advanced Content based Image Retrieval for Fashion
Tewodros Mulugeta Dagnew, Umberto Castellani
 
Audiovisual Liveness Detection

Aleksandr Melnikov, Rasim Akhunzyanov, Oleg Kudashev, Eugene Luckyanets

 

Poster session 5: Biomedical Applications & Video Analysis

Fully Automatic Brain Tumor Segmentation by using Competitive EM and Graph Cut
Valentina Pedoia, Sergio Balbi, Elisabetta Binaghi
 
An Automatic Method for Metabolic Evaluation of Gamma Knife Treatments
Alessandro Stefano, Salvatore Vitabile, Giorgio Russo, Massimo Ippolito, Franco Marletta, Corrado D'Arrigo, Davide D'Urso, Maria Gabriella Sabini, Orazio Gambino, Roberto Pirrone, Edoardo Ardizzone, Maria Carla Gilardi
 
Spinal canal and spinal marrow segmentation by means of the Hough Transform of special classes of curves
Annalisa Perasso, Cristina Campi, Anna Maria Massone, Mauro Beltrametti
 
A New Graph-Based Method for Automatic Segmentation
Laura Gemme, Silvana Dellepiane
 
Color Spaces in Data Fusion of Multi-Temporal Images
Roberta Ferretti, Silvana Dellepiane
 
TraGEN: A Tool for Generation of Synthetic Time-Lapse Image Sequences of Living Cells
Vladimir Ulman, Zoltán Orémuš, David Svoboda
 
Automatic Image Analysis and Classification for Urinary Bacteria Infection Screening
Paolo Andreini, Simone Bonechi, Monica Bianchini, Alessandro Mecocci, Vincenzo Di Massa
 
LBP-TOP for volume lesion classification in breast DCE-MRI
Gabriele Piantadosi, Roberta Fusco, Antonella Petrillo, Mario Sansone, Carlo Sansone
 
Kernel Centered Alignment Supervised Metric for Multi-Atlas Segmentation
Mauricio Orbes-Arteaga, David Cárdenas-Peña, Mauricio A. Alvarez, Alvaro A. Orozco, Germán Castellanos-Dominguez
 
A New Approach to Detect Use of Alcohol Through Iris Videos Using Computer Vision
Hedenir Pinheiro, Ronaldo Costa, Eduardo Camilo, Anderson Soares, Rogerio Salvini, Gustavo Laureano, Fabrizzio Soares, Gang Hua
 
Selection of Temporal Features for Event Detection in Smart Security
Niki Martinel, Danilo Avola, Claudio Piciarelli, Christian Micheloni, Marco Vernier, Luigi Cinque, Gian Luca Foresti
 
Recognition of Human Movements with Pressure Floor Sensors
Martino Lombardi, Roberto Vezzani, Rita Cucchiara
 
Object Detection & Tracking from fixed and mobile platforms
Giovanni Garibotto, Francesco Buemi
 
 
 
Foreground detection robust against cast shadows in outdoor daytime environment
Akari Sato, Masato Toda, Masato Tsukada
 
A Tool to Support the Creation of Datasets of Tampered Videos
Edoardo Ardizzone, Giuseppe Mazzola
 
Cognition helps vision: recognizing biological motion using invariant dynamic cues
Nicoletta Noceti, Alessandra Sciutti, Giulio Sandini
 
Egocentric Object Tracking: an Odometry-Based Solution
Stefano Alletto, Giuseppe Serra, Rita Cucchiara
 
En plein air visual agents
Marco Gori, Marco Lippi, Marco Maggini, Stefano Melacci, Marcello Pelillo
 
Modalities Combination for Italian Sign Language Extraction and Recognition
Bassem Seddik, Sami Gazzah, Najoua Essoukri Ben Amara
 
Abnormality Detection with Improved Histogram of Oriented Tracklets
Hossein Mousavi, Moin Nabi, Hamed Kiani Galoogahi, Alessandro Perina, Vittorio Murino

 

 

 

Proceedings

 springer

 springer

ICIAP 2015 Conference and Workshops Proceedings are now available here

Partners

UniVe
UniGe
Girpr
IIT

Endorsed by

Iapr
PAMI Technical Committee
Regione Liguria
Comune Genova Liguria

The conference is organized by

IIT-logo-v3-pavis

Twitter

ICIAP2015

RT @vmurino: #ICIAP2015 is over. Thx to all organization and support people, and to the participants of course. See you in Catania in 2017!