Abstract Deep Convolutional Neural Networks have been adopted for salient object
detection and achieved the state-of-the-art performance. Most of the previous works …

Although deep models have greatly improved the accuracy and robustness of image
segmentation, obtaining segmentation results with highly accurate boundaries and fine …

This letter presents a novel approach for extracting accurate outlines of individual buildings
from very high-resolution (0.1-0.4 m) optical images. Building outlines are defined as …

Given that existing salient object detection methods cannot effectively predict the fine
contours of salient objects when extracting local or global contexts and features, we propose …

In general, salient object detection (SOD) datasets have ambiguity due to annotation
accuracy and human subjectivity in determining saliency. Since this data uncertainty causes …

In this paper, we propose a real-time method for accurate salient closed boundary tracking
via a combination of shape constraints and perceptual grouping on edge fragments …

The training of the SOD model relies on abundant annotated data, which needs laborious
and expensive manual labeling. The generated pseudo-labels for reducing the annotation of …

In this paper, we consider the problem of tracking noisy two-dimensional level curves using
only the instantaneous measurements of the field, taken by two mobile agents, without the …

Simulating shadow interactions between real and virtual objects is important for augmented
reality (AR), in which accurately and efficiently detecting real shadows from live videos is a …

Video salient object detection (VSOD) aims at locating the most attractive objects in a video
by exploring the temporal and spatial features. Despite the progress made in existing VSOD …