Dense interest points

135 citations recorded by the source corpus.

How researchers see this paper

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

What Makes for Effective Detection Proposals? (2015, neutral): “F”
How good are detection proposals, really? (2014, background): “Today however, with the increase of computing power, it is standard practice to use dense feature extraction instead [27].”
High-level event recognition in unconstrained videos (2012, background): “In this direction, Tuytlaars proposed a hybrid selection strategy [140] where the author demonstrated how the advantages of both sampling schemes can be efficiently combined to improve recognition performance.”
Incorporating visual adjectives for image classification (2016, background): “Typical examples include Differential of Gaussian (DoG) [2], Hessian/Harris Af ﬁ ne [5], Maximally Stable Extremal Region (MSER) [6] operators and dense interest points [7].”
Towards Reversal-Invariant Image Representation (2017, background): “Although these descriptors can be automatically detected using operators such as DoG (Lowe 2004) and MSER (Matas et al. 2004), the dense sampling strategy (Bosch et al. 2006; Tuytelaars 2010) often works better on classification tasks.”
Invariant Image-Based Species Classification of Butterflies and Reef Fish (2015, background): “• Dense interest points (DIP) SIFT: Tuytelaars [14] proposed a hybrid approach in which image patches are densely sampled on a regular grid and at multiple scales.”
Unsupervised object discovery via self-organisation (2012, methodology): “11 T.Tuytelaars, 2010.”