Abstract 3D instance segmentation, with a variety of applications in robotics and augmented
reality, is in large demands these days. Unlike 2D images that are projective observations of …

Facial Expression Recognition (FER) in the wild poses significant challenges due to realistic
occlusions, illumination, scale, and head pose variations of the facial images. In this article …

One of the essential layers in most Convolutional Neural Networks (CNNs) is the pooling
layer, which is placed right after the convolution layer, effectively downsampling the input …

Exposed surface for buildings (ESB), which refers to exposed surfaces with traces of
building construction, often leads to urban dust. Accurate ESB detection is important for …

Edge information has been proven to be effective for remedying the unclear boundaries of
salient objects. Current salient object detection (SOD) methods usually utilize edge …

Vision-based anomaly inspection plays a crucial role in the efficient maintenance of millions
of kilometers of railway, with rail segmentation, a key step in such anomaly detection for …

Due to the high representational efficiency, superpixel largely reduces the number of image
primitives for subsequent processing. However, superpixel is scarcely utilized in recent …

Medical image segmentation plays a crucial role in assisting diagnosis. However, the
inherent low contrast and noise in medical images make it challenging to achieve accurate …

As one of the most popular preprocessing steps in computer vision fields, superpixel
generation algorithm has been extensively studied in recent years. Researchers have to find …

Objective. Due to the blurry edges and uneven shape of breast tumors, breast tumor
segmentation can be a challenging task. Recently, deep convolution networks based …