Picking the best DAISY

By Simon A. J. Winder, Gang Hua, Matthew A. Brown. 2009

312 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Aggregating Local Image Descriptors into Compact Codes (2012, methodology): “First, this representation benefits from powerful local descriptors, such as the SIFT descriptor [7] or more recent ones [8], [9], [10].”
MatchNet: Unifying feature and metric learning for patch-based matching (2015, unknown): “[35] for learning descriptors.”
HPatches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors (2017, background): “This further highlights the need for using a multitask benchmark to complement training and testing on PhotoTourism, which is done in vast majority of recent papers and is similar to the veriﬁcation task here.”
Learning visual feature descriptors for dynamic lighting conditions (2014, methodology): “For the DAISY descriptor we use learned parameters provided by [16], specifically the “T1-4-2r8s” version as it has an output dimension of 68 and computation time comparable with our learned descriptors.”
Adaptive deconvolutional networks for mid and high level feature learning (2011, background): “Interestingly, many of the successful representations are quite similar [18], essentially involving the calculation of edge gradients, followed by some histogram or pooling operation.”
Total recall II: Query expansion revisited (2011, background): “Virtually all aspects of particular object BoW-type retrieval have been intensively studied: feature detectors and descriptors [14, 5, 25, 15, 16], vocabulary construction [23, 18, 21, 9, 17], spatial verification and re-ranking [21, 9], document metric learning [12, 10, 6] and dimensionality reduct”
WarpNet: Weakly Supervised Matching for Single-View Reconstruction (2016, background): “These works focus on matching images of the same instance (for example, the Statue of Liberty [31]) from various viewpoints, while we match deformable objects of different instances exhibiting a wide variety of appearances.”
Face recognition with learning-based descriptor (2010, background): “Recently, face recognition has attracted much research effort [9, 25, 26, 10, 11, 13, 19, 20, 30, 32] due to the progresses of local descriptors [6, 16, 17, 22, 27, 28, 29, 30] and increasing demands of real-world applications, such as face tagging on the desktop [5] or the Internet(1).”
Unsupervised Learning of Discriminative Attributes and Visual Representations (2016, methodology): “, DAISY [50]) are very valuable to detect image contours or even their enclosed objects.”
Three things everyone should know to improve object retrieval (2012, background): “Others have learnt better visual descriptors (than SIFT) [32] or better metrics for descriptor comparison and quantization [25].”
DeepStore: In-Storage Acceleration for Intelligent Queries (2019, background): “Recent advancement in deep neural networks (DNNs) and the explosive increase and ubiquitous accessibility of data has enabled intelligent queries in multiple applications [16, 20, 25, 30, 48, 51, 58, 59, 67, 85, 93, 95, 100, 106].”
Hierarchical Convolutional Deep Learning in Computer Vision (2013, methodology): “Low-level image features such as SIFT [80], HOG [26] or DAISY [139] have been shown to be useful for tasks such as image matching and retrieval [15].”
Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification (2013, methodology): “Scale-invariant DoG keypoints [19] are extracted and 32dimensional DAISY descriptors [31] are computed for these keypoints.”
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning (2019, methodology): “Indicators like false positive rate and mean average precision have been widely used for evaluating the performance of descriptors [1, 39].”
Learning 6D Object Pose Estimation Using 3D Object Coordinates (2014, background): “More recently a trend has been to learn interest points [22,10], descriptors [30], and matching [14,19,1].”
Learning local feature descriptors with triplets and shallow convolutional neural networks (2016, methodology): “The evaluation is done with two different evaluation metrics frequently found in the literature, patch pair classification success in terms of ROC curves [22], and mean average precision in terms of correct matching of feature points between pairs of images [16].”
BRIEF: Binary Robust Independent Elementary Features (2010, methodology): “Quantization is used for the same purpose in [6,7].”