iV&LSS 2016: Deep Learning
The 2nd Summer School on Integrating Vision and Language
21–24 March 2016, University of Malta, Malta
Organised by ICT COST Action IC1307 The (iV&L Net) – Combining Computer Vision and Language Processing For Advanced Search, Retrieval, Annotation and Description of Visual Data
About iV&L Net:
The explosive growth of visual and textual data (both on the Internet and held in private repositories by diverse institutions and companies) has led to urgent requirements in terms of search, processing and management of digital content. Solutions for providing access to or mining such data depend on the semantic gap between vision and language being bridged, which in turn calls for expertise from two largely unconnected fields: Computer Vision (CV) and Natural Language Processing (NLP). The central goal of the iV&L Net COST Action is to build a European CV/NLP research community, particularly targeting 4 focus
themes: (i) Integrated Modelling of Vision and Language for CV and NLP Tasks; (ii) Applications of Integrated Models; (iii) Automatic Generation of Image & Video Descriptions; and (iv) Semantic Image & Video Search. iV&L Net organises and funds annual training schools, workshops, technical meetings, researcher exchange visits, data/task benchmarking, and industry/end-user liaison.
About iV&LSS 2016:
The 2016 Summer School on Integrating Vision and Language is the second in a series of Summer Schools aimed at bringing together Vision and Language researchers and to provide the opportunity for cross-disciplinary teaching and learning. The aim is that each summer school will build on the last, collectively providing a comprehensive body of information and learning materials about data, methods and applications in Computer Vision, Language Processing and their intersection, focusing particularly on the integration of vision and language processing.
The particular focus of iV&LSS16 will be deep learning for Vision and Language Integration. Through lectures and hands-on sessions, the summer school will cover the state of the art in using deep learning methods within our two disciplines, Computer Vision and Natural Language Processing.
Highlights from the iV&LSS16 Programme:
Lecture tutorials and practical sessions by (programme and topics to be finalised):
* Cees Snoek, Amsterdam University: Basics of Neural Networks
* Krystian Mikolajczyk, Imperial College London: Deep Learning Architectures
* NVIDIA Practical Sessions on Deep Learning
* Andrea Vedaldi, University of Oxford: Deep Learning for Applications with emphasis on CV
* Nal Kalchbrenner, Google DeepMind: Deep Learning for Applications with emphasis on NLP
* Richard Socher, MetaMind Inc: Deep learning for CV-NLP Integration Applications with emphasis on NLP
* Mario Fritz: Deep learning for CV-NLP integration applications with emphasis on CV
* Research Presentations
* Poster Session
* Student Session
* Social programme including tours of Valletta, lunches and dinners
The iV&LSS’16 training school is open to anyone interested in its topics, free of charge. A limited number of researchers resident in COST countries will be able to receive financial support to enable them to attend the training school.
If you are interested in attending, please look out for the first call for participation which will contain instructions for how to sign up for iV&LSS’16.
Training School Organisers:
Anya Belz, Brighton University, UK
Jordi Gonzalez, Autonomous University of Barcelona, Spain Sien Moens, Leuven University, Belgium Adrian Muscat, Malta University, Malta Katerina Pastra, ISLP Athens, Greece Mike Rosner, Malta University, Malta