Authors are encouraged to submit previously unpublished research full length 6 pages (to be presented as oral presentation) to one of CBMI 2017 four special sessions. Submissions are handled with the same system used for the conference.
- Deep Learning for Multimedia indexing
- Multimedia for Cultural Heritage
- Sparse Data Machine Learning for Domains in Multimedia
- Synergetic media production architecture
Important dates
- Special session paper submission deadline: extended to March 14, 2017;
- Notification of acceptance: April 28, 2017;
- Camera-ready papers due: May 23, 2017.
Call for “Deep Learning for Multimedia indexing” special session papers
Authors are encouraged to submit previously unpublished research papers related to the use of deep learning for content-based multimedia indexing. Works on multimodal (e.g. audio+image or image+text) deep learning are especially encouraged.
Topics include (but are not limited to):
- Deep convolutional networks for multimedia indexing;
- Use of learnt features for multimedia indexing;
- Hybrid (“classical” and deep) systems for multimedia indexing;
- Deep learning for audio indexing;
- Deep learning for text indexing;
- Multimodal deep learning for video indexing;
- Deep convolutional networks for object localization;
- Understanding deep networks for multimedia indexing;
- Recurrent neural network architectures for multimedia;
- End-to-end learning for speech and audio processing.
- Works on multimodal (e.g. audio+image or image+text) deep learning are especially encouraged.
Organizers:
- Georges Quénot – CNRS, France (Georges.Quenot at imag dot fr);
- Laurent Besacier – University of Grenoble-Alpes, France (Laurent.Besacier at imag dot fr).
Call for “Multimedia for Cultural Heritage” special session papers
This special session fits the aims of CBMI to bring together the various communities involved in all aspects of content-based multimedia indexing for retrieval, browsing, management, visualization and analytics, with the specific focus on the hot topics in multimedia applied to Cultural Heritage.
Topics include (but are not limited to):
- Media content analysis and search
- Interactive 3D media and immersive environments
- Multi-modal multimedia computing systems and human-machine interaction
- Multimedia databases and digital libraries
- Multimedia applications and services
- Hardware and software for multimedia systems also in mobile scenarios
- Security issues in the presentation and distribution of cultural information
Organizers:
- Costantino Grana – University of Modena, Italy (costantino.grana@unimore.it)
- Lorenzo Baraldi – University of Modena, Italy (lorenzo.baraldi@unimore.it)
Call for “Sparse Data Machine Learning for Domains in Multimedia” special session papers
The scope of this session is machine learning in areas that come with a lack of data, such as medicine. This fact makes it very challenging to apply machine learning methods and get meaningful results. Especially the highly praised and used deep learning is very depending on a lot of good training data. In this special session we would like to ask researchers to submit papers that address these problems.
Topics include (but are not limited to):
- Traditional machine learning vs Deep learning
- Machine Learning on small data
- Deep learning with small datasets
- Unsupervised machine learning
- Data creation
- Data annotation
- Knowledge transfer
- Areas with small multimedia datasets (for example medicine, psychology)
- Multimedia tools and applications in fields with lack of data (for example medicine, psychology)
Organizers:
- Konstantin Pogorelov – Simula Research Laboratory, Norway (konstantin@simula.no)
- Duc-Tien Dang-Nguyen – Dublin City University, Ireland (duc-tien.dang-nguyen@dcu.ie)
- Michael Riegler – Simula Research Laboratory, Norway (michael@simula.no)
- Luca Piras – University of Cagliari, Italy ( luca.piras@diee.unica.it)
- Paolo Rota – Vienna University of Technology, Austria (rota@caa.tuwien.ac.at)
- Pål Halvorsen – Simula Research Laboratory, Norway (paalh@simula.no)
Call for “Synergetic media production architecture” special session papers
Recent technological advances in UHD broadcasting and mobile social sharing, coupled with over fifty years of research and development in multimedia systems technology, mean that the time is now right for research into how user-sourced media can enrich the conventional broadcasting experience.
Topics include (but are not limited to):
- Heterogeneous metadata extraction from media
- Time point correlation of content among disparate media sources
- Automatic metadata recommendation to UGC content
- Metadata enrichment of authored content using structured information
- User-centric sequencing of media for seamless consumption
- Context-centric media association of professional sources with UGC
- Evaluation procedures for QoE
Organizers:
- Ebroul Izquierdo – Queen Mary, University of London, UK (ebroul.izquierdo@qmul.ac.uk)
- Krishna Chandramouli – Queen Mary, University of London, UK (krishna.chandramouli@qmul.ac.uk)