CROSS MARSEIL 2015 - 2015 International Workshop on 3D Cross Media Analysis, Retrieval of Semantic Events, Immersion & Visualisation

The main objectives of this workshop is to bring together researchers working in the area of 3D image analysis, event detection, actions recognition, retrieval of activities (human or not) and search in large multimedia datasets of relevant event-based content. It also includes data for image processing in vision sensor networks, communication in social networks, crowdsourcing methods for image and video analysis and graph-based innovative techniques. Deep learning algorithms will be also included in the workshop.
Recently, it can be argued that the intelligence behind many pattern recognition and computer vision systems is mainly focused on two main approaches; (i) extraction of smart features able to efficiently represent the rich visual content and (ii) adoption of non-linear and adaptable (semi-supervised) learning strategies able to fill the gap between the extracted low level features and the high level concepts, humans use to perceive the content, (iii) deep learning architectures, (iv) distributed video processing across network of cameras. The feature extraction is a data dimensionality reduction strategy that addresses the difficulty that learning complexity grows exponentially upon a linear increase in the dimensionality of data. It is also clear that extraction of representational features is a challenging and application-dependent process. Non-representative features significantly affect the recognition accuracy, especially for complex and dynamic environments even though they are processed by highly non-linear feature transformation models. Thus, the main goal of this workshop is to seek original articles in the area of multimedia research in the direction of detecting and recognizing high level concepts, detecting objects across network of cameras.
Specific topics of interest.
New visual features suitable for specific events
Events detection from multiple cameras and across multiple sensors
Distributed tracking across a network of cameras
3D video streaming
3D retrieval
3D relevance feedback schemes
Semantic and event-based summarization of monitored video data
3-D Visualization and Computer animation
Gaming Technologies
e-Learning using 3D content
Deep machine learning in image analysis and multimedia applications
Architectures and prototypes for cognitive video supervision
Applications such as
3D TV scenarios
Video Surveillance
Assistive Living
Unmanned Aerial (UAV’s) Monitoring (UAV’s)
Cadastrial applications
Environmental issues
Organizers:
Prof. Anastasios D. Doulamis ? National Technical University of Athens, Greece
(adoulam-AT-cs.ntua.gr)
Prof. Charalabos Ioannidis ? National Technical University of Athens, Greece
(cioannid-AT-survey.ntua.gr.ntua.gr)
Prof. Tania Stathaki ?Imperial College, United Kingdom
(t [dot] stathaki-AT-imperial.ac.uk)
Prof. Nikolaos D. Doulamis ? National Technical University of Athens, Greece
(ndoulam-AT-cs.ntua.gr)
Prof. Nikos Komodakis ?Ecole des Ponts ?Paris Tech France
(nikos.komodakis-AT-enpc.fr)