Sensing and Modeling Human Behaviors In Complex Conversational Scenes

Understanding human behavior has been an intriguing topic studied by many disciplines, including social science, neuroscience, etc. Humans exhibit social behaviors, through for example, interacting, conversing, empathizing with each other. Systematically and scientifically studying these behaviors often requires granular observations and...

Conversation Group Detection With Spatio-Temporal Context

In this work, we propose an approach for detecting conversation groups in social scenarios like cocktail parties and networking events, from overhead camera recordings. We posit the detection of conversation groups as a learning problem that could benefit from leveraging the spatial context of the surroundings, and the inherent temporal...

Multimodal Joint Head Orientation Estimation in Interacting Groups via Proxemics and Interaction Dynamics

Human head orientation estimation has been of interest because head orientation serves as a cue to directed social attention. Most existing approaches rely on visual and high-fidelity sensor inputs and deep learning strategies that do not consider the social context of unstructured and crowded mingling scenarios. We show that alternative...

Inverse-designed spinodoid metamaterials

After a decade of periodic truss-, plate-, and shell-based architectures having dominated the design of metamaterials, we introduce the non-periodic class of spinodoid topologies. Inspired by natural self-assembly processes, spinodoid metamaterials are a close approximation of microstructures observed during spinodal phase separation. Their...

A Modular Approach for Synchronized Wireless Multimodal Multisensor Data Acquisition in Highly Dynamic Social Settings

Existing data acquisition literature for human behavior research provides wired solutions, mainly for controlled laboratory setups. In uncontrolled free-standing conversation settings, where participants are free to walk around, these solutions are unsuitable. While wireless solutions are employed in the broadcasting industry, they can be...

Multimodal data collection for social interaction analysis in-the-wild

The benefits of exploiting multi-modality in the analysis of human-human social behaviour has been demonstrated widely in the community. An important aspect of this problem is the collection of data-sets that provide a rich and realistic representation of how people actually socialize with each other in real life. These subtle coordination...

Improving temporal interpolation of head and body pose using Gaussian process regression in a matrix completion setting

This paper presents a model for head and body pose estimation (HBPE) when labelled samples are highly sparse. The current state-of-the-art multimodal approach to HBPE utilizes the matrix completion method in a transductive setting to predict pose labels for unobserved samples. Based on this approach, the proposed method tackles HBPE when...

Dynamic Finite Element Investigation of Wave Attack on Sea Dikes: A Coupled Approach using Plate and Volume Elements

Approximately 400 kilometres of Dutch sea dikes are protected by bituminous concrete revetments to prevent damage from erosion and repeated wave attacks during storms. The numerical analysis of sea dikes subjected to cyclic wave loading needs to consider the behaviour of the bituminous concrete revetment, and the behaviour of the subsoil...

Numerical simulation of wave attack on sea dike with asphalt concrete revetment

The numerical simulation of wave attack on a sea dike with an asphalt concrete revetment during a severe storm is carried out using the dynamic Finite Element Method. When wave loads attack the revetment during such a storm, both the revetment and the underlying soil may be damaged. The two-phase flow equations are considered, to study the...