Domain adaptation methods for 2D human pose estimation typically require...
Scene understanding using multi-modal data is necessary in many applicat...
We study the problem of how to identify samples from unseen categories
(...
Imitation learning seeks to circumvent the difficulty in designing prope...
Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for...
While supervised techniques in re-identification are extremely effective...
Most person re-identification methods, being supervised techniques, suff...