STSM Reports

iV&L Net STSMs and reports

Title: Multimedia document classification using multi-modal features

Beneficiary :Yaakov HaCohen-Kerner, Jerusalem College of Technology, Jerusalem, Israel

Host: Information Technologies Institute, Centre for Research and Technology, Thessaloniki, Greece

Period: 15/02/2015 to 19/02/2015

Download Report


Title: Semantic space models of fast mapping in cross-modal concept learning

Beneficiary :Raquel Fernandez Rovira, Institute for Logic, Language and Computation University of Amsterdam, The Netherlands

Host: University of Trento, Italy

Period: 15/02/2015 to 15/03/2015

Download Report


Title: Auto-tagging and categorisation of life-logging photos

Beneficiary :Stavri Nikolov, Imagga Technologies Ltd, Bulgaria

Host: University of Barcelona, Spain

Period: 15/06/2015 to 28/06/2015

Download Report


Title: Synchronizing Visual and Natural Language Grammars for Pattern Analysis and Description

Beneficiary :Adrian Muscat, University of Malta, Malta

Host: University of Brighton, UK

Period: 30/04/2015 to 09/05/2015

Download Report


Title: Weakly supervised learning for multi-modal distributional semantics

Beneficiary :Barbara Plank, University of Copenhagen, Denmark

Host: University of Trento, Italy

Period: 25/05/2015 to 29/05/2015

Download Report


Title: Recognition of actions and activities for automatic video captioning

Beneficiary :Marina Ivasic-Kos, University of Rijeka, Croatia

Host: Computer Vision Center, Univ. Autònoma de Barcelona, Spain

Period: 9/05/2015 to 26/05/2015

Download Report


Title: Recognition of human actions and activities for automatic video description

Beneficiary :Miran Pobar, University of Rijeka, Croatia

Host: Computer Vision Center, Univ. Autònoma de Barcelona, Spain

Period: 19/05/2015 to 26/05/2015

Download Report


Title: First step for accurate 3D body classification

Beneficiary :Gholamreza Anbarjafari, University of Tartu, Estonia

Host: University of Barcelona, Spain

Period: 24/08/2015 to 11/09/2015

Download Report


Title: Personal photo organization

Beneficiary :Mariella Dimicolli, University of Barcelona, Spain

Host: Imagga Technologies, Bulgaria

Period: 28/09/2015 to 11/10/2015

Download Report


Title: The role of attentional, linguistic and visual features on landmarks selection

Beneficiary :Adriana Baltaretu, Tilburg University, The Netherlands

Host: The University of Edinburgh, UK

Period: 28/09/2015 to 09/10/2015

Download Report


Title: Designing a shared task on multi-modal machine translation

Beneficiary :Lucia Specia, University of Sheffield, UK

Host: University of Amsterdam, The Netherlands

Period: 22/11/2015 to 26/11/2015

Download Report


Title: Vision and Language in Social Media

Beneficiary :Francesco Barbieri, Universitat Pompeu Fabra, Barcelona, Spain

Host: University of Trento, Italy

Period: 08/01/2016 to 07/04/2016

Abstract: The work that was carried out during the STSM may be divided in two phases. The first one was focused on emojis, small images used as text, in four languages, namely American English, British English, Spanish and Italian. In the second phase, Francesco worked on multimodal systems to discover relations between profile pictures and timelines of Twitter users.

Download Report


Title: Multimodal Anger and Joy Recognition by Audiovisual Information

Beneficiary :Gholamreza Anbarjafari, University of Tartu, Estonia

Host: Lodz University of Technology, Poland

Period: 16/04/2016 to 24/04/2016

Abstract: The main objective of STSM is to develop more robust and more accurate anger and joy recognition strategy by applying multimodal recognition through combining acoustic and facial cues with body gestures that involve shoulders, arms, and hands.

Download Report


Title: Training and Evaluating Multilingual and Multimodal Models

Beneficiary :Iacer Calixto, Dublin City University, Ireland

Host: University of Amsterdam, The Netherlands

Period: 04/04/2016 to 15/04/2016

Abstract: The aim of the STSM was two-fold: (i) to present some of my previous work to the host research group; (ii) to work collaboratively on a multi-task approach integrating natural language processing (NLP) models using multimodal information.

Download Report


Title: Multimedia document classification using multi-modal features and/or text classification (and/or clustering) using Machine Learning Methods

Beneficiary :Yaakov HaCohen-Kerner, Jerusalem College of Technology, Israel

Host: Durham University, Durham, United Kingdom

Period: 03/04/2016 to 07/04/2016

Abstract: The aim of this STSM was mainly to establish a new joint research in the area of multimodal (textual and visual features) classification and/or clustering of documents. The goal was to investigate whether various combinations of both textual and visual features can improve the classification (clustering) accuracy

Download Report