ProgramsView all programs
From the news
- Chancellor Amma Addresses the Parliament of World’s Religions
- Amrita Students Qualify for the European Mars Rover Challenge
Publication Type : Conference Paper
Publisher : 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) (2015)
Source : 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) (2015)
Keywords : accuracy, automatic child behaviour observation, automatic high-level feature extraction, behavioural sciences computing, child engagement level, child engagement measurement, computational modeling, Feature extraction, hand gestures, head poses, hidden conditional random fields, Hidden Markov models, hidden state marginals, image sequences, learning (artificial intelligence), low-level optical flow based features, multimodal dyadic behaviour dataset, optical flow based hidden structure behaviour learning, Pediatrics, Predictive models, social interaction, Support vector machines, SVM-based model learning, Videos
Campus : Coimbatore
School : School of Engineering
Department : Electrical and Electronics
Year : 2015
Abstract : Due to the challenges in automatically observing child behaviour in a social interaction, an automatic extraction of high-level features, such as head poses and hand gestures, is difficult and noisy, leading to an inaccurate model. Hence, the feasibility of using easily obtainable low-level optical flow based features is investigated in this work. A comparative study involving high-level features, baseline annotations of multiple modalities and the low-level features is carried out. Optical flow based hidden structure learning of behaviours is strongly discriminatory in predicting a child's engagement level in a social interaction. A two-stage approach of discovering the hidden structures using Hidden Conditional Random Fields, followed by learning an SVM-based model on the hidden state marginals is proposed. This is validated by conducting experiments on the Multimodal Dyadic Behaviour Dataset and the results indicate a state of the art classification performance. The insights drawn from this study indicate the robustness of the low-level feature approach towards engagement behaviour modelling and can be a good substitute in the absence of accurate high-level features.
Cite this Research Publication : S. S. Rajagopalan, Dr. Oruganti Venkata Ramana Murthy, Goecke, R., and Rozga, A., “Play with me - Measuring a child's engagement in a social interaction”, in 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 2015.