Visual representation learning is ubiquitous in various real-world applications, including
visual comprehension, video understanding, multi-modal analysis, human-computer …

The integration of machine/deep learning and sensing technologies is transforming
healthcare and medical practice. However, inherent limitations in healthcare data, namely …

Skeleton sequence representation learning has shown great advantages for action
recognition due to its promising ability to model human joints and topology. However, the …

Existing visual question answering methods often suffer from cross-modal spurious
correlations and oversimplified event-level reasoning processes that fail to capture event …

Video self-supervised learning is a challenging task, which requires significant expressive
power from the model to leverage rich spatial-temporal knowledge and generate effective …

Recently, developing automated video surveillance systems (VSSs) has become crucial to
ensure the security and safety of the population, especially during events involving large …

Human action recognition and video summarization represent challenging tasks for several
computer vision applications including video surveillance, criminal investigations, and sports …

Existing vision-based action recognition is susceptible to occlusion and appearance
variations, while wearable sensors can alleviate these challenges by capturing human …

Video anomaly detection is a challenging task owing to the rare and diverse nature of
abnormal events. However, most of the existing methods only learn the normality in a single …

To help agents reason about scenes in terms of their building blocks, we wish to extract the
compositional structure of any given scene (in particular, the configuration and …