Sister Practices: Non-Normative Experiences of Time and Technology

This chapter summarises some of the learning from a material practice that sits in a sisterly manner next to architecture. Drawing on feminist writing and the experiences of women in professional life more generally, the chapter will examine how mainstream understanding of time and technology limit the engagement of those people in society who do not fit given norms. The chapter argues that when we examine such concepts in more detail and expand them to reflect diverse experiences those very same concepts offer new potentials and innovative openings for the progression of disciplines such as architecture.

Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance.