Graphs naturally appear in numerous application domains, ranging from social analysis,
bioinformatics to computer vision. The unique capability of graphs enables capturing the …

Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Deep learning-based models have been shown to outperform human beings in many
computer vision tasks with massive available labeled training data in learning. However …

An integral part of video analysis and surveillance is temporal activity detection, which
means to simultaneously recognize and localize activities in long untrimmed videos …

Scene graph generation is an important visual understanding task with a broad range of
vision applications. Despite recent tremendous progress, it remains challenging due to the …

Continual Learning aims to learn a single model on a sequence of tasks without having
access to data from previous tasks. The biggest challenge in the domain still remains …

The learning of the deep networks largely relies on the data with human-annotated labels. In
some label insufficient situations, the performance degrades on the decision boundary with …

With the advances of data-driven machine learning research, a wide variety of prediction
problems have been tackled. It has become critical to explore how machine learning and …

Recent works have shown that unstructured text (documents) from online sources can serve
as useful auxiliary information for zero-shot image classification. However, these methods …