Wei Xia

TL;DR: A framework to train embedding models, called backward-compatible training (BCT), is proposed as a first step towards backward compatible representation learning, and models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.

TL;DR: An experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change, is developed.

TL;DR: This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian and summarizes the winning solutions for all three tracks, and presents discussions on open problems and potential research directions in these topics.

TL;DR: In this paper, the authors developed an experimental method for measuring algorithmic bias of face analysis algorithms, which directly manipulates the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change.

TL;DR: An online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span is proposed, by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects.