Graph Neural Networks (GNNs) have gained momentum in graph representation learning
and boosted the state of the art in a variety of areas, such as data mining (eg, social network …

This paper presents a general scheme for enhancing the convergence and performance of
DETR (DEtection TRansformer). We investigate the slow convergence problem in …

We present a novel deep hypergraph modeling architecture (called DHM-Net) for feature
matching in this paper. Our network focuses on learning reliable correspondences between …

Document object detection is a challenging task due to layout complexity and object
diversity. Most of existing methods mainly focus on vision information, neglecting …

Exploiting relationships between objects and (or) labels under graph message passing
mechanism to facilitate object detection has been widely investigated in recent years …

In the field of object detection, due to the complexity of realistic scenarios, the objects are
mostly obscured and semantic-confusable. The existing CNNs-based object detectors focus …

Human pose prediction is vital for robot applications such as human–robot interaction and
autonomous control of robots. Recent prediction methods often use deep learning and are …

Pavement crack detection plays a crucial role in ensuring traffic safety and prolonging
service life. Cracks often exhibit irregular curved contours, with their local details submerged …

There is a growing demand for an intelligent system to continually learn knowledge from a
data stream. Continual learning requires both the preservation of previous knowledge (ie …

Semantic Segmentation in side-scan sonar images (SSS-Seg) is an emerging topic and
plays important function in sonar image interpretation. However, due to the interference of …