Results 311 to 320 of about 311,283 (352)
Some of the next articles are maybe not open access.
Learning Selective Self-Mutual Attention for RGB-D Saliency Detection
Computer Vision and Pattern Recognition, 2020Saliency detection on RGB-D images is receiving more and more research interests recently. Previous models adopt the early fusion or the result fusion scheme to fuse the input RGB and depth data or their saliency maps, which incur the problem of ...
Nian Liu, Ni Zhang, Junwei Han
semanticscholar +1 more source
SMU-Net: Saliency-Guided Morphology-Aware U-Net for Breast Lesion Segmentation in Ultrasound Image
IEEE Transactions on Medical Imaging, 2021Deep learning methods, especially convolutional neural networks, have been successfully applied to lesion segmentation in breast ultrasound (BUS) images.
Zhenyuan Ning +4 more
semanticscholar +1 more source
A Multimodal Saliency Model for Videos With High Audio-Visual Correspondence
IEEE Transactions on Image Processing, 2020Audio information has been bypassed by most of current visual attention prediction studies. However, sound could have influence on visual attention and such influence has been widely investigated and proofed by many psychological studies.
Xiongkuo Min +5 more
semanticscholar +1 more source
Evaluating saliency map explanations for convolutional neural networks: a user study
International Conference on Intelligent User Interfaces, 2020Convolutional neural networks (CNNs) offer great machine learning performance over a range of applications, but their operation is hard to interpret, even for experts.
Ahmed Alqaraawi +4 more
semanticscholar +1 more source
Select, Supplement and Focus for RGB-D Saliency Detection
Computer Vision and Pattern Recognition, 2020Depth data containing a preponderance of discriminative power in location have been proven beneficial for accurate saliency prediction. However, RGB-D saliency detection methods are also negatively influenced by randomly distributed erroneous or missing ...
Miao Zhang +4 more
semanticscholar +1 more source
What Do Different Evaluation Metrics Tell Us About Saliency Models?
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016How best to evaluate a saliency model's ability to predict where humans look in images is an open research question. The choice of evaluation metric depends on how saliency is defined and how the ground truth is represented.
Z. Bylinskii +4 more
semanticscholar +1 more source
The (Un)reliability of saliency methods
Explainable AI, 2017Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction.
Pieter-Jan Kindermans +7 more
semanticscholar +1 more source
Unified Image and Video Saliency Modeling
European Conference on Computer Vision, 2020Visual saliency modeling for images and videos is treated as two independent tasks in recent computer vision literature. While image saliency modeling is a well-studied problem and progress on benchmarks like SALICON and MIT300 is slowing, video saliency
Richard Droste, Jianbo Jiao, J. Noble
semanticscholar +1 more source
Marketing Science, 2008
Brand salience—the extent to which a brand visually stands out from its competitors—is vital in competing on the shelf, yet is not easy to achieve in practice. This study proposes a methodology to determine the competitive salience of brands, based on a model of visual search and eye-movement recordings collected during a brand search experiment.
Van der lans, Ralf. +2 more
openaire +3 more sources
Brand salience—the extent to which a brand visually stands out from its competitors—is vital in competing on the shelf, yet is not easy to achieve in practice. This study proposes a methodology to determine the competitive salience of brands, based on a model of visual search and eye-movement recordings collected during a brand search experiment.
Van der lans, Ralf. +2 more
openaire +3 more sources
Graphical Models and Image Processing, 1995
Abstract The distance transform has been used in computer vision for a number of applications such as matching and skeletonization. This paper proposes two things: (1) a multiscale distance transform to overcome the need to choose the appropriate scale and (2) the addition of various saliency factors such as edge strength, length, and curvature to ...
Rosin, Paul L., West, Geoff A. W.
openaire +2 more sources
Abstract The distance transform has been used in computer vision for a number of applications such as matching and skeletonization. This paper proposes two things: (1) a multiscale distance transform to overcome the need to choose the appropriate scale and (2) the addition of various saliency factors such as edge strength, length, and curvature to ...
Rosin, Paul L., West, Geoff A. W.
openaire +2 more sources