Compositionality, the ability to combine existing concepts and generaliz...
Identifying humans with their walking sequences, known as gait recogniti...
This paper addresses the problem of human rendering in the video with
te...
We propose a self-supervised shared encoder model that achieves strong
r...
Gait recognition, which identifies individuals based on their walking
pa...
Adversarial patch attacks mislead neural networks by injecting adversari...
We explore object detection with two attributes: color and material. The...
Phrase grounding models localize an object in the image given a referrin...