Abstract Three-dimensional (3D) object recognition is widely used in automated driving,
medical image analysis, virtual/augmented reality, artificial intelligence robots, and other …

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-learning based salient object detection methods achieve great progress. However, the
variable scale and unknown category of salient objects are great challenges all the time …

Saliency detection is one of the basic challenges in computer vision. Recently, CNNs are the
most widely used and powerful techniques for saliency detection, in which feature maps …

In this paper, we present a hypergraph neural networks (HGNN) framework for data
representation learning, which can encode high-order data correlation in a hypergraph …

RGB-D salient object detection (SOD) is usually formulated as a problem of classification or
regression over two modalities, ie, RGB and depth. Hence, effective RGB-D feature …

Hypergraph learning is a technique for conducting learning on a hypergraph structure. In
recent years, hypergraph learning has attracted increasing attention due to its flexibility and …

We explore the potential of pooling techniques on the task of salient object detection by
expanding its role in convolutional neural networks. In general, two pooling-based modules …

The large availability of depth sensors provides valuable complementary information for
salient object detection (SOD) in RGBD images. However, due to the inherent difference …

Fully convolutional neural networks (FCNs) have shown outstanding performance in many
dense labeling problems. One key pillar of these successes is mining relevant information …