Large-scale labeled training datasets have enabled deep neural networks to excel across a
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …

Understanding human actions in visual data is tied to advances in complementary research
areas including object recognition, human dynamics, domain adaptation and semantic …

Deep learning has produced state-of-the-art results for a variety of tasks. While such
approaches for supervised learning have performed well, they assume that training and …

Influenced by the great success of deep learning via cloud computing and the rapid
development of edge chips, research in artificial intelligence (AI) has shifted to both of the …

Deep neural networks suffer from performance decay when there is domain shift between
the labeled source domain and unlabeled target domain, which motivates the research on …

The performance of a classifier trained on data coming from a specific domain typically
degrades when applied to a related but different one. While annotating many samples from …

Domain adaptation aims to leverage knowledge from a well-labeled source domain to a
poorly labeled target domain. A majority of existing works transfer the knowledge at either …

Currently, unsupervised heterogeneous domain adaptation in a generalized setting, which
is the most common scenario in real-world applications, is under insufficient exploration …

Recently, considerable effort has been devoted to deep domain adaptation in computer
vision and machine learning communities. However, most of existing work only concentrates …

Transfer learning has been demonstrated to be effective for many real-world applications as
it exploits knowledge present in labeled training data from a source domain to enhance a …