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 …

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 …

Images can convey rich semantics and induce various emotions in viewers. Recently, with
the rapid advancement of emotional intelligence and the explosive growth of visual data …

Simulation-to-real domain adaptation for semantic segmentation has been actively studied
for various applications such as autonomous driving. Existing methods mainly focus on a …

Machine-learning models are key to modern biology, yet models trained on one dataset are
often not generalizable to other datasets from different cohorts or laboratories due to both …

In many practical applications, it is often difficult and expensive to obtain enough large-scale
labeled data to train deep neural networks to their full capability. Therefore, transferring the …

Emotion recognition in user-generated videos plays an important role in human-centered
computing. Existing methods mainly employ traditional two-stage shallow pipeline, ie …

Due to its robust and precise distance measurements, LiDAR plays an important role in
scene understanding for autonomous driving. Training deep neural networks (DNNs) on …

A non-invasive fetal electrocardiogram (FECG) is used to monitor the electrical pulse of the
fetal heart. Decomposing the FECG signal from the maternal ECG (MECG) is a blind source …

Existing domain adaptation methods on visual sentiment classification typically are
investigated under the single-source scenario, where the knowledge learned from a source …