Saliency, Scale and Image Description

By Timor Kadir, M. Brady. International Journal of Computer Vision, 2001

1,302 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/254be2055a84c4d80c4c8eb8e6090b3977cc6fb6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

DRAMMS: Deformable Registration via Attribute Matching and Mutual-Saliency Weighting (2009, neutral): “As scale and orientation are closely related to the distinctiveness of attributes [28], the multi-scale and multi-orientation attributes are more likely to render each voxel distinctively identifiable, therefore reducing ambiguities in attribute-based voxel matching.”
Multi-Region Probabilistic Histograms for Robust and Scalable Identity Inference (2009, background): “Based on [9] we define an L1-norm based distance measure between faces A and B:”
Simultaneous image classification and annotation (2009, positive): “Each image is represented as a bag of “codewords” r1:N, which are obtained by running the k-means algorithm on patches of the images [ 15 , 18].”
BASNet: Boundary-Aware Salient Object Detection (2019, neutral): “image segmentation/editing [53, 25, 11, 54] and manipulation [24, 43], visual tracking [32, 52, 55] and user interface optimization [12].”
Efficient Salient Region Detection with Soft Image Abstraction (2013, background): “While saliency implies uniqueness, the opposite might not always be true [33, 42].”
Behavior recognition via sparse spatio-temporal features (2005, background): “Kadir and Brady [14] approach feature detection with the specific goal of detecting features for object recognition.”
Randomized Clustering Forests for Image Classification (2008, background): “Entropy-based measures emphasize the information difference of regions [29], [47], [18] or the rarity of features in the feature space [23] more.”
Salient object detection by composition (2011, methodology): “We propose to detect salient objects by directly measuring the saliency of an image window in the original image and adopt the well established sliding window based object detection paradigm.”
A Review on Human Activity Recognition Using Vision-Based Method (2017, methodology): “The 2D salient point detection was ﬁ rst proposed by Kadir and Brady in [35].”
OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning (2007, background): “Kadir and Brady (2001) salient point detector offers compact representations of the image, which makes computation more efﬁcient for our framework.”