Across surveillance technologies today computer vision is a critical component of how they function. Through the collection of videos and images, information is extracted by these systems to classify and analyse, often capturing far more than the individual intends to reveal. In this process, human behaviour is distilled into neatly defined categories which oversimplify the complexities of our corporeal selves.
This work focuses on Affection Mapping which is a branch of Machine Learning concerned with classifying emotions which are complex; evolving around and in response to our families, relationships, environments, and personal histories. Distilling this into an algorithm exposes the creation of a rigid taxonomy in their pursuit to classify a messy physical world. These systems inadvertently reveal an unfamiliar umwelt—a new lens through which meaning is extracted and reality is interpreted. By examining this computational gaze, we can observe how these systems function, their inherent biases, and how they influence and bleed into our physical world.
The installation is built as a computational system composed of computer vision and machine learning models. A dataset of archived footage is processed through the system to detect, segment, and extract features from each frame, with each feature represented as a multi-dimensional vector or embedding. This data is then sorted, reduced in dimensionality, and mapped into a two-dimensional space, creating a human-readable representation of the system's latent space. Users can interact and explore the dataset by selecting various constellations of emotions, prompting the system to navigate towards its closest match.
Cailean Finn is a media artist and creative technologist currently based in Dublin, Ireland. His practice is centred around investigating computational aesthetics, histories, and processes embedded in socio-technological systems – ranging from Artificial Intelligence, to Creative Coding, and Physical Computing. Currently, he is exploring the emergent behaviours of computational systems; experimenting with simulations as a medium for these investigations.
