Imperial College London embodies and delivers world class scholarship, education and research in science, engineering and medicine, with particular regard to their application in industry, commerce and healthcare.
It has been ranked 3rd in Europe and 10th in the world overall, according to the Times Higher Education World University Rankings 2013-2014. It fosters interdisciplinary working internally and collaborates widely externally, especially in Europe. It consists of a number of departments including Electrical & Electronic Engineering, Mathematics, and Computing. The Department of Computing (DoC) is involved in this proposal. It has a number of world-class research sections, amongst others, in Machine Learning, Visual Information Processing and Distributed Computing.
The primary interest of the Visual Information Processing (VIP) section, who participate in the DE-ENIGMA proposal, is to pursue fundamental research and real-world applications of Computer Vision. This research has led to over 1000 publications, including over 250 peer reviewed journal papers. Much of this research has been sponsored by the UK Government’s Research Councils and the European Union.
Team leader:
- Maja Pantic: Scientific and technological advisor of the DE-ENIGMA project.
Team members:
- Ognjen Rudovic: Key researcher
- Jie Shen: Affect-sensitive human-robot interaction and cloud-based affective computing systems
- Shiyang Cheng: Assistant in experiment data collection
- Robert Walecki: Analysis of human facial behavior
- Sebastian Kaltwang: Recognition of subtle facial movement
- Stefanos Eleftheriadis: DE-ENIGMA partner
- Christos Georgakis: Dynamic behavior and affect analysis
- Teresa Ng: Finance and Research Manager
Objectives and tasks:
- DE-ENIGMA Database collection, annotation and release
- To collect and release of a publicly available benchmark multilingual dataset of annotated facial, bodily, vocal and verbal recordings of interactions between children with autism and their counterpartners (therapist, robot, parent).
- DE-ENIGMA data acquisition
- DE-ENIGMA data annotation
- DE-ENIGMA database design release and maintenance
- To collect and release of a publicly available benchmark multilingual dataset of annotated facial, bodily, vocal and verbal recordings of interactions between children with autism and their counterpartners (therapist, robot, parent).
- DE-ENIGMA Perception
- To focus in robust, context-sensitive and real time machine analysis of facial, bodily and vocal cues in unconstrained recording conditions that are atypical and abruptly changing as caractheristic for children with autism.
- Environmentally robust, personalised facial features
- Audio-visual detection of nonverbal vocalisations
- To focus in robust, context-sensitive and real time machine analysis of facial, bodily and vocal cues in unconstrained recording conditions that are atypical and abruptly changing as caractheristic for children with autism.
- DE-ENIGMA Reasoning
- This objective addresses the problem of automatic reasoning about behavioural patterns of the child as observed in unconstrained recordings of facial, vocal/verbal and bodily expressions, and based on the features extracted in the objective “DE-ENIGMA Perception”.
- Multi-modal estimation of affect, interest and stress levels
- Multi-Modal rapport recognition
- Context transfer
- Confidence measures
- This objective addresses the problem of automatic reasoning about behavioural patterns of the child as observed in unconstrained recordings of facial, vocal/verbal and bodily expressions, and based on the features extracted in the objective “DE-ENIGMA Perception”.
- DE-ENIGMA Integration and Evaluation
- To specify the functional requirements, interactions and constraints of DE-ENIGMA: construct the integrated DE-ENIGMA platform and assess the impact DE-ENIGMA skill training compared to traditional therapies on autistic children’s socio-emotional skills.
- Specifications of functional requirements, interactions and constraints
- Construction and integration of the DE-ENIGMA platform
- Final evaluation of the integrated DE-ENIGMA system
- To specify the functional requirements, interactions and constraints of DE-ENIGMA: construct the integrated DE-ENIGMA platform and assess the impact DE-ENIGMA skill training compared to traditional therapies on autistic children’s socio-emotional skills.
- DE-ENIGMA Dissemination, Communication and Exploitation
- To create public, scientific and industrial awareness of the project achievements. Dissemination and exploitation activities will be performed in strict relation with all the technical activities
- Dissemination strategy
- Data management plan and dissemination of software and datasets
- Organisation of challenges and benchmarking
- To create public, scientific and industrial awareness of the project achievements. Dissemination and exploitation activities will be performed in strict relation with all the technical activities
- DE-ENIGMA Management
- To implement all technical, financial and administrative aspects of the project plan to ensure that it is executed in fulfillment of the contract with the European Commission.
- Project leadership and coordination
- Administrative and financial management
- Quality assurance and risk management
- Preparation for review of progress
- To implement all technical, financial and administrative aspects of the project plan to ensure that it is executed in fulfillment of the contract with the European Commission.
SW7 2AZ LONDON
United Kingdom