Conference technical program
Program at a glance (click to download the PDF version)
June 15 | June 16 | June 17 | |
---|---|---|---|
08:00- 08:50 | Registrations | Registrations | Registrations |
08:50- 09:00 | Welcome | Day opening | Day opening |
09:00- 10:00 |
Keynote 1 "Web-scale video content search" by Alexander Hauptmann Chair: Henning Müller |
Keynote 2 "Civic multimedia, crowdsourcing, and the public good" by Daniel Gatica-Perez Chair: Guillaume Gravier |
Panel "Multimedia analysis out of the box: new applications and domains" Guests: Alexander Hauptmann, Guillaume Gravier, Martha Larson, Bernard Merialdo |
10:00- 10:30 | Coffee break (at the venue) | Coffee break (at the venue) | Coffee break (at the venue) |
10:30- 12:00 |
Oral session 1 Multimedia Modeling and Annotation Chair: Maia Zaharieva |
Oral session 3 Information Retrieval Chair: Markus Schedl |
Special session 3 Deep Learning for Multimedia Indexing Chair: Georges Quénot |
12:00- 14:00 | Lunch (at the venue) | Lunch (at the venue) | Lunch (at the venue) |
14:00- 15:30 |
Special session 1 Content-Based Image and Multimedia Analysis and Indexing for Healthcare Chairs: Jenny Benois-Pineau, Klaus Schöffmann |
Special session 2 Multimedia Indexing for eLearning Chair: Stephane Marchand-Maillet |
Oral session 4 Users and Knowledge in Multimedia Applications Chair: Alexandre Benoit |
15:30- 16:00 | Coffee break (at the venue) | Coffee break (at the venue) | Closing remarks |
16:00- 17:30 |
Oral session 2 Image and Video Classification Chair: Horia Cucu |
Group photo
Poster and demo session Chairs: Bogdan Boteanu, Andi Buzo |
|
17:30- 18:00 | |||
18:00- 19:00 | Bucharest City Tour | ||
19:00- | Welcome reception | Gala dinner |
Conference sessions
Keynote 1: Web-Scale Video Content Search Alexander Hauptmann, Carnegie Mellon University, USA
Chair: Henning Müller, University of Applied Sciences Western Switzerland, Switzerland
Even though the accuracy of content based video search systems (CBVS) has drastically improved, high accuracy systems tend to be too inefficient for interactive search. Therefore, to achieve real-time CBVS over millions of videos, we perform a comprehensive study on the different components in a CBVS system to understand the tradeoffs between accuracy and speed of each component. Directions investigated include exploring different low-level and semantics based features, testing different compression factors and approximations during video search, and understanding the time vs. accuracy trade-of. Semantic search in video is a novel and challenging problem in information and multimedia retrieval. Existing solutions are mainly limited to text matching, in which the query words are matched against the textual metadata generated by users. This talk will contrast approaches for content search both with example videos and without, using only text queries. The system relies on substantial video content analysis and allows for both low-level and semantic search over a large collection of videos. We share our observations and lessons in building such a system, which may be instrumental in guiding the design of future systems for search in video. Extensive experiments on very large archives consisting of more than 2,000 hours of short videos showed that through a combination of effective features, highly compressed representations, and one iteration of reranking, our proposed system can achieve an 10,000-fold speedup while retaining 80% accuracy of a state-of-the-art CBVS system. Over 1 million videos, our system can complete example-based search in one second with a single core.
Keynote 2: Civic Multimedia, Crowdsourcing, and the Public Good Daniel Gatica-Perez, Idiap-EPFL, Switzerland
Chair: Guillaume Gravier, IRISA, France
The engagement of young people in local civic concerns has educational, social, and economic implications. There is an entire open agenda of civic issues that multimedia research can support, spanning media collection, content analysis, and media creation and repurposing. In the specific context of cities in the developing world, how do youth perceive their urban environment? How do they react to problems like security, accessibility, or waste management? What issues are they more sensitive about? What problems go unnoticed? How can mobile and social tech be used to support young people document these issues, enable self and group reflections, and contribute to community action? In the talk, I will present a mobile crowdsourcing framework where young people help render visible urban issues that matter to them. Integrating photos and video, online experiments, multimedia analysis, and media creation, the goal is to enable a reflection process through which discussions and proposals to address such issues can emerge. I will argue for the need to think beyond single disciplines, and advocate for the opportunities that emerge from working with communities, both to contribute to the public good and to advance multimedia research in cities.
Panel: Multimedia analysis out of the box: new applications and domains
Alexander Hauptmann, Carnegie Mellon University, USA Guillaume Gravier, IRISA, France Martha Larson, Delft University of Technology, The Netherlands Bernard Merialdo, EURECOM, France
Discussions will evolve around new, recent and emerging areas and applications of multimedia: what multimedia analysis and retrieval is contributing? what is gaining? what is needed based on the domain and user requirements? what are the actual and future challenges? what are the lessons learnt so far? (are just a few of the elaborated questions).
Oral session 1: Multimedia Modeling and Annotation
Chair: Maia Zaharieva, University of Vienna & Vienna University of Technology, Austria
- Bahjat Safadi, Philippe Mulhem, Georges Quénot and Jean-Pierre Chevallet, Lifelog Semantic Annotation using Deep Visual Features and Metadata-Derived Descriptors
- Miguel-Ángel Fernández-Torres, Iván González-Díaz and Fernando Díaz-De-María, A Probabilistic Topic Approach for Context-Aware Visual Attention Modeling
- Satoru Ishikawa and Jorma Laaksonen, Comparing and Combining Unimodal Methods for Multimodal Recognition
Oral session 2: Image and Video Classification
Chair: Horia Cucu, University Politehnica of Bucharest, Romania
- Federico Becattini, Lorenzo Seidenari and Alberto Del Bimbo, Indexing Ensembles of Exemplar-SVMs with Rejecting Taxonomies
- Ionut Cosmin Duta, Jasper Uijlings, Tuan Anh Nguyen, Kiyoharu Aizawa, Alexander Hauptmann, Bogdan Ionescu and Nicu Sebe, Histograms of Motion Gradients for Real-time Video Classification
- Omar Seddati, Stéphane Dupont and Saïd Mahmoudi, DeepSketch 2: Deep Convolutional Neural Networks for Partial Sketch Recognition
- Lukas Diem and Maia Zaharieva, Model-based Video Content Representation
Oral session 3: Information Retrieval
Chair: Markus Schedl, Johannes Kepler University, Austria
- Ilias Gialampoukidis, Anastasia Moumtzidou, Dimitris Liparas, Stefanos Vrochidis and Yiannis Kompatsiaris, A Hybrid Graph-based and Non-linear Late Fusion Approach for Multimedia Retrieval
- Ahmad Khwileh and Gareth Jones, Investigating Segment-Based Query Expansion for User-Generated Spoken Content Retrieval
- Marwa Thlithi, Julien Pinquier, Thomas Pellegrini and Régine André-Obrecht, Filterbank Coefficients Selection for Segmentation in Singer Turns
Oral session 4: Users and Knowledge in Multimedia Applications
Chair: Alexandre Benoit, Polytech Annecy Chambéry, France
- Soumyadeb Chowdhury, Md Sadek Ferdous and Joemon Jose, A User-Study Examining Visualization of Lifelogs
- Cesar Pantoja and Ebroul Izquierdo, A Novel Architecture of Semantic Web Reasoner based on Transferable Belief Model
- Michael Riegler, Vamsidhar Reddy Gaddam, Martha Larson, Ragnhild Eg, Pål Halvorsen and Carsten Griwodz, Crowdsourcing as Self Fulfilling Prophecy: Influence of Discarding Workers in Subjective Assessment Tasks
Special session 1: Content-Based Image and Multimedia Analysis and Indexing for Healthcare
Chairs: Jenny Benois-Pineau, University Bordeaux, France & Klaus Schöffmann, Klagenfurt University, Austria
- Michael Riegler, Konstantin Pogorelov, Pål Halvorsen, Thomas de Lange, Carsten Griwodz, Peter Thelin Schmidt, Sigrun Losada Eskeland and Dag Johansen, EIR - Efficient Computer Aided Diagnosis Framework for Gastrointestinal Endoscopies
- Katia Charrière, Gwénolé Quellec, Mathieu Lamard, David Martiano, Guy Cazuguel, Gouenou Coatrieux and Béatrice Cochener, Real-time Multilevel Sequencing of Cataract Surgery Videos
- Souad Chaabouni, Jenny Benois, François Tison and Chokri Ben Amar, Prediction of Visual Attention with Deep CNN for Studies of Neurodegenerative Diseases
- Manfred Jürgen Primus, Klaus Schöffmann and Laszlo Boeszoermenyi, Temporal Segmentation of Laparoscopic Videos into Surgical Phases
- Alexis Zubiolo, Eric Debreuve, Damien Ambrosetti, Philippe Pognonec and Xavier Descombes, Is the Vascular Network Discriminant Enough to Classify Renal Cell Carcinoma?
Special session 2: Multimedia Indexing for eLearning
Chair: Stephane Marchand-Maillet, University of Geneva, Switzerland
- Sotiris Karavarsamis, Dimitrios Ververidis, Giannis Chantas, Spiros Nikolopoulos and Yiannis Kompatsiaris, Classifying Salsa Dance Steps from Skeletal Poses
- Sheetal Rajgure, Vincent Oria, Pierre Gouton, Reza Curtmola, Edina Renfro-Michel and Krithika Raghavan, Indexing Multimedia Learning Materials in Ultimate Course Search
- Subhasree Basu, Yi Yu and Roger Zimmermann, Fuzzy Clustering of Lecture Videos Based on Topic Modeling
Special session 3: Deep Learning for Multimedia Indexing
Chair: Georges Quénot, Laboratory of Informatics of Grenoble, France
- Nicolas Voiron, Alexandre Benoit, Patrick Lambert and Bogdan Ionescu, Deep Learning vs Spectral Clustering into an Active Clustering with Pairwise Constraints Propagation
- Jordi Pons, Thomas Lidy and Xavier Serra, Experimenting with Musically Motivated Convolutional Neural Networks
- Titouan Lorieul, Antoine Ghorra and Bernard Merialdo, Static and Dynamic Autopsy of Deep Networks
Poster and demos
Posters
Chair: Bogdan Boteanu, University Politehnica of Bucharest, Romania
- Vu-Lam Nguyen, Ngoc-Son Vu and Philippe-Henri Gosselin, A Scattering Transform combination with Local Binary Pattern for Texture Classification
- Mathias Lux, Nektarios Anagnostopoulos and Chryssanthi Iakovidou, Spatial Pyramids for Boosting Global Features in Content Based Image Retrieval
- Markus Schedl, David Hauger, Marko Tkalcic, Mark Melenhorst and Cynthia C.S. Liem, A Dataset of Multimedia Material About Classical Music: PHENICX-SMM
- Anastasia Moumtzidou, Ilias Gialampoukidis, Theodoros Mironidis, Dimitris Liparas, Stefanos Vrochidis and Yiannis Kompatsiaris, A Multimedia Interactive Search Engine based on Graph-based and Non-linear Multimodal Fusion
- Roxane Licandro, Paolo Rota, Michael Reiter and Martin Kampel, Flow Cytometry Based Automatic MRD Assessment in Acute Lymphoblastic Leukaemia: Longitudinal Evaluation of Time-Specific Cell Population Models
- Xinchao Li, Peng Xu, Yue Shi, Martha Larson and Alan Hanjalic, Simple Tag-based Subclass Representations for Visually-varied Image Classes
- Nikos Zikos, Anastasios Delopoulos and Dafni Maria Vasilikari, From Textual Queries to Visual Queries
- Henrique Silva, Zenilton Patrocinio Jr, Guillaume Gravier, Laurent Amsaleg, Arnaldo Araújo and Silvio Guimaraes, Near-Duplicate Video Detection Based on an Approximate Similarity Self-Join Strategy
- Miroslav Macík, Jakub Lokoc, Premysl Cech and Tomas Skopal, Particle Physics Model for Content-based 3D Exploration
- Alexandru Caranica, Horia Cucu and Andi Buzo, Exploring an Unsupervised, Language Independent, Spoken Document Retrieval System
Demos
Chair: Andi Buzo, Infineon Technologies & University Politehnica of Bucharest, Romania
- Ranveer Joyseeree, Roger Schaer and Henning Müller, A Demo of Multimodal Medical Retrieval
- David Hauger and Markus Schedl, Music Tweet Map: A Browsing Interface to Explore the Microblogosphere of Music
- Sheetal Rajgure, Vincent Oria, Krithika Raghavan, Hardik Dasadia, Sai Shashank Devannagari, Reza Curtmola, James Geller, Edina Renfro-Michel and Soon Chun, UCS: Ultimate Course Search
- Michael Riegler, Konstantin Pogorelov, Mathias Lux, Pål Halvorsen, Carsten Griwodz, Thomas de Lange and Sigrun Losada Eskeland, Explorative Hyperbolic-Tree-Based Clustering Tool for Unsupervised Knowledge Discovery
- Gabriel de Oliveira Barra, Mathias Lux and Xavier Giro-I-Nieto, Large Scale Content-Based Video Retrieval with LIvRE
- Alexandros Bampoulidis, Joao Palotti, Jon Brassey, Mihai Lupu, Sokratis Metallidis and Allan Hanbury, Interactive Exploration of Healthcare Queries