Dr Xinshao Wang's PhD project was funded by University Special Research Scholarship and sponsored by a company that provides many services on intelligent vision recognition.
Xinshao Wang is working on core deep learning techniques with applications to visual recognition:
(1) Deep metric learning: to learn discriminative and robust image/video representations for downstream tasks, e.g., image/video retrieval and image/video clustering;
(2) Robust deep learning: robust learning and inference under adverse conditions, e.g., label noise, missing labels (semi-supervised learning), out-of-distribution training examples, sample imbalance, etc;
(3) Computer vision: video/set-based person re-identification; image/video classification/retrieval/clustering.