Trento - Italy - Sept 10th 2019
SCOPE - In retail environments, understanding consumer behaviour is of great importance and one of the keys to success for retailers. While the retail environment has several favourable characteristics that support computer vision, such as reasonable lighting, the large number and diversity of products sold, as well as the potential ambiguity of shoppers' movements, mean that accurately measuring shopper behaviour is still challenging. Over the past years, machine-learning and feature-based tools for people counting as well as interactions analytic and re-identification were developed with the aim of learning shopper skills. However, after moving into the era of multimedia big data, machine-learning approaches evolved into deep learning approaches, which are a more powerful and efficient way of dealing with the complexities of human behaviour. The goal of this workshop is to encourage and highlight novel strategies and original research in computer vision and patter recognition for shoppers’ behavior understanding, building a network between European universities and industries and a roadmap for future deep learning applications.
The workshop calls for submissions addressing, but not limited to, the following topics:
• Deep learning architectures for large scale shopper behaviour understanding
• Deep learning for shoppers' feature representation
• Deep learning for facial analysis
• Deep learning for object recognition
• Deep learning for scene understanding
• Deep learning for activity recognition
• Deep learning for semantic segmentation
• Deep learning for generative modeling
• Deep learning for biometrics
• Multi-modal deep learning
• Face detection and tracking from video
• Multi-face clustering from video
• Applications of video face recognition
• Automatic video annotation and summarization
• Context-aware machine learning and image understanding
• Dataset for Retail
• Edge/Fog/Cloud Architecture for Deep Learning Applications
• Other artificial intelligence methods on shopper behaviour analysis
The submission and review process will be managed with the EasyChair system. DeepRetail2019 Submission Website
The length of the papers is maximum 8 pages. Papers will be selected by a single blind (reviewers are anonymous) review process based on their originality, relevance, and clarity of presentation.
Accepted papers will be included in the ICIAP 2019 Conference Proceedings, which will be published by Springer in the Lecture Notes in Computer Science series (LNCS). Every accepted paper requires that at least one author is registered with regular registration fee and attending the workshop.
Templates and paper formatting instructions are available on the ICIAP 2019 web page.
Instructions and Templates
Trento - Italy - Sept 10th 2019
The Whorkshop will be held in Trento in conjunction with ICIAP 2019.
Tuesday, September 10, 2019 09:00-13:00 Location: Sala 1
Venue detailed info: https://event.unitn.it/iciap2019/
09:00 -09:20 Welcome and opening remarks
Oswald Lanz, Fondazione Bruno Kessler - General Chair ICIAP 2019
Emanuele Frontoni, Marina Paolanti - Università Politecnica delle Marche - DEEPRETAIL 2019
09:20-10:00 (Invited Talk) Title: A brief history of AI projects of GfK market research and how to organize an enterprise for today`s challenges of data science
Vanya Kostova, Principal Product Owner, Global PoS (GfK - Germany)
Markus Iwanczok, Product Owner, Global PoS (GfK - Germany)
10.00-10:20 Title: Collecting retail data using a deep learning identification experience
Salvatore La Porta, Fabrizio Marconi (JEF), Isabella Lazzini (Huawei)
10:20-10:40 Paper Title: Semantic 3D Object Maps for everyday robotic retail inspection
Marina Paolanti, Roberto Pierdicca, Massimo Martini, Francesco Di Stefano, Christian Morbidoni, Adriano Mancini, Eva Savina Malinverni, Emanuele Frontoni, Primo Zingaretti (UNIVPM)
10:40 Coffee Break
11:00-11:20 Title: The vending shopper science Lab: deep learning for consumer research
Fioravante Allegrino (CIV - Sogeda), Patrizia Gabellini, Luigi Di Bello, Marco Contigiani, Valerio Placidi (Grottini Lab)
11:20-11:40 Title: An IOT edge-fog-cloud architecture for vision based pallet integrity
Raffaele Vaira, Rocco Pietrini, Roberto Pierdicca, Primo Zingaretti, Adriano Mancini, Emanuele Frontoni (UNIVPM)
11:40-12:00 Title: A large scale trajectory dataset for shopper behaviour understanding
Patrizia Gabellini, Mauro D'Aloisio, Matteo Fabiani, Valerio Placidi (Grottini Lab)
12:00-12.50 Panel Discussion
Sebastiano Battiato (UNICT) , Patrizia Gabellini (Grottini Lab), Giovanni Maria Farinella (UNICT), Cosimo Distante (CNR), Luigi di Stefano (UNIBO), Vanya Kostova (GfK), Markus Iwanczok (GfK), Massimo De Benedictis (IPSOS), Primo Zingaretti (UNIVPM)
SCIENTIFIC COMMITTEE
• Emanuele Frontoni, Department of Information Engineering, Università Politecnica delle Marche
• Sebastiano Battiato, Dipartimento di Matematica ed Informatica, Università di Catania
• Cosimo Distante, Institute of Applied Sciences and Intelligent Systems - ISASI CNR
• Marina Paolanti, Department of Information Engineering, Università Politecnica delle Marche
• Luigi Di Stefano, Dipartimento di Informatica - Scienza e Ingegneria, Università di Bologna
• Giovanni Marina Farinella, Dipartimento di Matematica ed Informatica, Università di Catania
• Annette Wolfrath, GFK Verein - Germany
• Primo Zingaretti, Department of Information Engineering, Università Politecnica delle Marche
INDUSTRIAL COMMITTEE
• Massimo De Benedictis, IPSOS - France
• Luigi Caniglia, Acqua & Sapone- Italy
• Rinaldo Rinaldi, Conad Adriatico - Italy
• Fioravante Allegrino , Sogeda - Italy, Poland
• Francesco Mammana, Huawei - China, Italy
• Julian Oberndoerfer, ERA Europe - Germany
• Stefan Sheman - GKF - Germany
• Claudia Cavarischia, Philip Morris Intl - Swiss
• Mario Galietti, P&G - Italy, US
• Luca Di Camillo, Luxottica - Italy
• Joe Baer, Zen Genius - US
• Nicola Evoli, Grottini - Italy, US