Pain in Human and Non-Human Animals:
From Evolutionary Theories to AI Tools
17th April 2026 at 4pm
Webconference only
Online seminar on pain in human and non-human animals on Friday, April 17th by Lola Cañamero.
Lola Cañamero, full Professor, Paris-Seine INEX Chair Neuroscience and Robotics at ETIS Lab (ETIS – CNRS/CY Cergy Paris University/ENSEA), chair of the AAAC Education and Early Career Committee, member of the AS1 and AS3 projects, has been organising online seminar series since 2022 with the Association for the Advancement of Affective Computing.
The speaker will be:
Marwa Mahmoud is a Senior Lecturer (Associate Professor) in Socially Intelligent Technologies at the University of Glasgow. Her research focuses on computer vision, multimodal machine learning, and behavioural AI for modelling affective and behavioural signals in humans and animals. She develops interpretable AI systems for real-world applications in mental health, wellbeing, and animal welfare, including vision-based analysis of pain and emotional states in animals. She directs the Behavioural AI Lab at Glasgow, where her research centres on AI for Social Good, combining machine learning and behavioural science to understand and model complex behaviours in real-world environments. Her work has been supported by funding from the Scottish Universities Life Sciences Alliance (SULSA), COST (European Cooperation in Science and Technology), and industry collaborations with Jaguar Land Rover and Qualcomm. She served as President of the Association for the Advancement of Affective Computing (AAAC) and was General Chair of ACII 2024. She was recently an invited speaker and panelist at the NIH Pain in Animals Workshop (PAW 2025) and currently serves as Associate Guest Editor for IEEE Transactions on Affective Computing.
Summary
In “The Expression of the Emotions in Man and Animals” (1872), Darwin argued that many emotional and behavioural expressions have evolutionary origins and are shared, to varying degrees, between humans and other animals. Pain is a striking example: while it serves vital protective and social functions, its expression varies across contexts. Prey animals often suppress visible signs to avoid predation, while in humans pain behaviours can signal a need for care—although biases in perception are evident and can influence how pain is recognised and responded to. In this talk, she will explore how computational methods can shed light on these challenges. Drawing on my research in multimodal behaviour modelling in humans and animals, she will show how facial and bodily expressions can be automatically analysed to capture subtle indicators of discomfort and distress. She will also present their work on automatic pain assessment in facial expressions of sheep, alongside pose and behaviour detection methods in both sheep and cattle, which demonstrate how computer vision methods can provide objective measures for the early detection of pain or distress. Key challenges in this domain – such as data scarcity, noisy labels, and the need for interpretability – are common to both human and animal pain assessment, and she will discuss the modelling techniques they employ to tackle these issues.
Other Seminars
