Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by

By Matthijs C. Dorst. 2011

11,848 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Object Detection Networks on Convolutional Feature Maps (2015, methodology): “101 The Selective Search paper [4] relies on spatial pyra- 102 mid features [20] on dense SIFT vectors [21] and an 103 additive kernel SVM.”
Taskonomy: Disentangling Task Transfer Learning (2018, background): “Keypoint algorithmns usually consist of two parts, both a keypoint detector and some local patch descriptor which is invariant across multiple images [24, 4, 32].”
An Analysis of Scale Invariance in Object Detection - SNIP (2017, background): “Scale space theory [35, 26] advocates learning representations that are invariant to scale and the theory has been applied to many problems in the history of computer vision [4, 30, 28, 21, 14, 5, 23].”
Recognition of Transitive Actions with Hierarchical Neural Network Learning (2016, methodology): “For the representation of objects, we use SIFT features [14] that yield invariance to translation, rotation and scaling transformations and, to some extent, robustness to occlusions.”
Rotational Projection Statistics for 3D Local Surface Description and Object Recognition (2013, background): “Beyond object recognition from 2D images (Brown and Lowe, 2003; Lowe, 2004; Mikolajczyk and Schmid, 2004), 3D object recognition has been extensively investigated during the last two decades due to the availability of low cost scanners and high speed computing devices (Mamic and Bennamoun 2002).”
Understanding Traffic Density from Large-Scale Web Camera Data (2017, methodology): “For comparison, we extract dense SIFT features [22] using VLFeat [32].”
Detecting Avocados to Zucchinis: What Have We Done, and Where Are We Going? (2013, methodology): “It uses an image classification system with dense SIFT features and color statistics [13], a Fisher vector representation [16], and a linear SVM classifier, plus additional insights from [2, 17], combined with the deformable parts-based model (DPM) [9] which has been the dominant model for generic o”
ResNet or DenseNet? Introducing Dense Shortcuts to ResNet (2020, background): “Inspired by the success of these seminal works, the research focus of the community has shifted from feature engineering [26, 7] to network design engineering and numerous new network architectures have come out to boost the performance of DNNs.”
ACTIVE: Activity Concept Transitions in Video Event Classification (2013, background): “The features may include local image descriptors [13], motion descriptors [8] [9] [23] or audio descriptors.”
Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural Networks (2014, methodology): “This operation is similar to a gradients extractor when computing the SIFT or HOG feature [7], [8].”
Vision-Aided Inertial Navigation for Spacecraft Entry, Descent, and Landing (2009, methodology): “However, the scale and rotation invariance of the SIFT keys, which increases the processing requirements, is not necessary in the EDL scenario considered here.”
Automated Crack Detection on Concrete Bridges (2016, methodology): “Finding maxima in scale space is a well established method to find the best scale for a visual feature [27]–[29].”
Transformation Pursuit for Image Classification (2014, methodology): “This is an interesting find- 200 400 600 SGD Iterations (in thousands) 5 15 25 T op -1 A cc ur ac y (% ) T1 +T2 (crop5) +T3 (flip) +T4 (crop1) +T5 (crop6) +T6(crop0) 200 400 600 800 SGD Iterations (in thousands) 20 25 30 35 40 T op -5 A cc ur ac y (% ) T1 +T2 (flip) +T3 (crop0) +T4 (homo2) +T5 (crop”
Conformer: Local Features Coupling Global Representations for Visual Recognition (2021, background): “Local features and their descriptors [34, 27, 35], which are compact vector representations of local image neighborhoods, have been the building blocks of many computer vision algorithms.”