Conventional machine learning algorithms suffer the problem that the model trained on existing data fails to generalize well to the data sampled from other distributions. To tackle this issue, unsu…
Spectral clustering (SC) has become one of the most widely-adopted clustering algorithms, and been successfully applied into various applications. We in this work explore the problem of spectral cl…
Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributi…
Zero-shot learning for visual recognition, which approaches identifying unseen categories through a shared visual-semantic function learned on the seen categories and is expected to well adapt to u…
Kinship verification is a very important technique in many real-world applications, e.g., personal album organization, missing person investigation and forensic analysis. However, it is extremely d…