Anthony Brown

Mani Kumar Tellamekala, Shashank Jaiswal, Thomas Smith et al.

Recognising expressive behaviours in face videos is a long-standing challenge in Affective Computing. Despite significant advancements in recent years, it still remains a challenge to build a robust and reliable system for naturalistic and in-the-wild facial expressive behaviour analysis in real time. This paper addresses two key challenges in building such a system: (1). The paucity of large-scale labelled facial affect video datasets with extensive coverage of the 2D emotion space, and (2). The difficulty of extracting facial video features that are discriminative, interpretable, robust, and computationally efficient. Toward addressing these challenges, this work introduces xTrace, a robust tool for facial expressive behaviour analysis and predicting continuous values of dimensional emotions, namely valence and arousal, from in-the-wild face videos. To address challenge (1), the proposed affect recognition model is trained on the largest facial affect video data set, containing $\sim$450k videos that cover most emotion zones in the dimensional emotion space, making xTrace highly versatile in analysing a wide spectrum of naturalistic expressive behaviours. To address challenge (2), xTrace uses facial affect descriptors that are not only explainable, but can also achieve a high degree of accuracy and robustness with low computational complexity. The key components of xTrace are benchmarked against three existing tools: MediaPipe, OpenFace, and Augsburg Affect Toolbox. On an in-the-wild benchmarking set composed of $\sim$50k videos, xTrace achieves 0.86 mean Concordance Correlation Coefficient (CCC) and on the SEWA test set it achieves 0.75 mean CCC, outperforming existing SOTA by $\sim$7.1\%.

Gustavo Berumen, Joel E. Fischer, Anthony Brown et al.

This study attempts to understand the use of Consumer Packaged Goods (CPG) in practice to obtain insights to develop design interventions that bring the CPGs into the Internet of Things. Our ultimate aim is to equip CPGs with a layer of smartness so that CPGs could collect information about their use and provide extra services and functionalities. With a practice perspective we developed an assemblage of methods to analyze and represent how people use CPGs. We chose cooking as our practice case and use an auto-ethnographic data sample to demonstrate the application of our methods. Despite the early stage of our study, our methods provide ways to get an understanding of how CPGs are used in practice and an opening to establish opportunities for design interventions.

Thomas Lodge, Anthony Brown, Andy Crabtree

We present the Databox application development environment or SDK as a means of enabling trusted IoT app development at the network edge. The Databox platform is a dedicated domestic platform that stores IoT, mobile and cloud data and executes local data processing by third party apps to provide end-user control over data flow and enable data minimisation. Key challenges for building apps in edge environments concern i. the complexity of IoT devices and user requirements, and ii. supporting privacy preserving features that meet new data protection regulations. We show how the Databox SDK can ease the burden of regulatory compliance and be used to sensitize developers to privacy related issues in the very course of building apps. We present feedback on the SDK's exposure to over 3000 people across a range of developer and industry events.