Results 1 to 10 of about 405,506 (261)
The Secrets of Salient Object Segmentation [PDF]
arXiv, 2014 In this paper we provide an extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets. Our analysis identifies serious design flaws of existing salient object benchmarks, called the dataset design bias, by over emphasizing the stereotypical concepts of saliency.
Yin Li +4 more
arxiv +8 more sources
EGNet:Edge Guidance Network for Salient Object Detection [PDF]
arXiv, 2019 Fully convolutional neural networks (FCNs) have shown their advantages in the salient object detection task. However, most existing FCNs-based methods still suffer from coarse object boundaries. In this paper, to solve this problem, we focus on the complementarity between salient edge information and salient object information.
Jiaxing Zhao +5 more
arxiv +3 more sources
Salient alternatives facilitate implicatures. [PDF]
PLoS ONE, 2022 Sentences can be enriched by considering what the speaker does not say but could have done, the alternative. We conducted two experiments to test whether the salience of the alternative contributes to how people derive implicatures.
Lewis Bott, Steven Frisson
doaj +3 more sources
Salient region detection through salient and non-salient dictionaries.
PLoS ONE, 2019 Low-rank representation-based frameworks are becoming popular for the saliency and the object detection because of their easiness and simplicity. These frameworks only need global features to extract the salient objects while the local features are ...
Mian Muhammad Sadiq Fareed +5 more
doaj +5 more sources
Salient Object Detection: A Benchmark [PDF]
IEEE Transactions on Image Processing, 2015 We extensively compare, qualitatively and quantitatively, 41 state-of-the-art models (29 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over seven challenging data sets for the purpose of benchmarking salient object ...
A. Borji +3 more
semanticscholar +7 more sources
Salient Object Detection With Pyramid Attention and Salient Edges [PDF]
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019 This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two key contributions.
Wenguan Wang +4 more
semanticscholar +4 more sources
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground [PDF]
ECCV 2018, 2018 We provide a comprehensive evaluation of salient object detection (SOD) models. Our analysis identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in low clutter.
Deng-Ping Fan +5 more
arxiv +6 more sources
Salient Object Detection: Integrate Salient Features in the Deep Learning Framework [PDF]
IEEE Access, 2019 Salient object detection in complex environments brings the challenge from the collections of large number of training images for deep learning algorithm.
Qixin Chen +4 more
doaj +2 more sources
Salient object detection: A survey [PDF]
Computational Visual Media, 2019 Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep understanding
Ali Borji +4 more
doaj +5 more sources
What is a salient object? A dataset and a baseline model for salient object detection [PDF]
IEEE Transactions on Image Processing, 2014 Salient object detection or salient region detection models, diverging from fixation prediction models, have traditionally been dealing with locating and segmenting the most salient object or region in a scene. While the notion of most salient object is sensible when multiple objects exist in a scene, current datasets for evaluation of saliency ...
arxiv +7 more sources