Basnet: Boundary-aware salient object detection

X Qin, Z Zhang, C Huang, C Gao… - Proceedings of the …, 2019 - openaccess.thecvf.com
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 …

Boundary-aware segmentation network for mobile and web applications

X Qin, DP Fan, C Huang, C Diagne, Z Zhang… - arXiv preprint arXiv …, 2021 - arxiv.org
Although deep models have greatly improved the accuracy and robustness of image
segmentation, obtaining segmentation results with highly accurate boundaries and fine …

Accurate outline extraction of individual building from very high-resolution optical images

X Qin, S He, X Yang, M Dehghan… - IEEE Geoscience and …, 2018 - ieeexplore.ieee.org
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 …

A contour self-compensated network for salient object detection

Y Wang, H Wang, J Cao - The Visual Computer, 2021 - Springer
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 …

Data and Model Uncertainty Aware Salient Object Detection

H Lee, S Lee, BC Song - IEEE Access, 2024 - ieeexplore.ieee.org
In general, salient object detection (SOD) datasets have ambiguity due to annotation
accuracy and human subjectivity in determining saliency. Since this data uncertainty causes …

[PDF][PDF] Real-Time Salient Closed Boundary Tracking using Perceptual Grouping and Shape Priors.

X Qin, S He, Z Zhang, M Dehghan, M Jägersand - BMVC, 2017 - researchgate.net
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 …

Active learning with sampling by joint global-local uncertainty for salient object detection

L Li, H Fu, X Xu - Neural Computing and Applications, 2023 - Springer
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 …

A modular approach to level curve tracking with two nonholonomic mobile robots

S Chatterjee, W Wu - … Design Engineering Technical …, 2019 - asmedigitalcollection.asme.org
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 …

Real-Time Shadow Detection From Live Outdoor Videos for Augmented Reality

Y Liu, X Zou, S Xu, G Xing, H Wei… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
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 …

Multi-stream Temporally Enhanced Network for Video Salient Object Detection

JL Ru, D Xu - 2023 IEEE 6th International Conference on …, 2023 - ieeexplore.ieee.org
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 …