Spatial pyramid matching

64 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.

Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, background): “…K Histo (x i , x j ) = 1 3 F ∈{C,S,T} K Histo F (x i , x j ) p (6) Hodosh, Young & Hockenmaier 3.3.2 The Pyramid Kernel K Py The spatial pyramid kernel (Lazebnik et al., 2009) is a generalization of the histogram kernel that captures similarities not just at a global, but also at a local level.”
Data-driven visual similarity for cross-domain image matching (2011, methodology): “Spatial Pyramid: For each image, we compute spatial pyramid [Lazebnik et al. 2009] representation with 3 pyramid levels using Dense-SIFT descriptors of 16x16 pixel patches computed over a grid with spacing of 8 pixels.”
Classification of Breast Cancer Based on Histology Images Using Convolutional Neural Networks (2018, methodology): “Thus, we decided to apply spatial pyramid matching [41], [42], which is an efficient extension of pyramid matching [43].”
Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (Extended Abstract) (2015, methodology): “In our experiments, we focus on developing and analyzing the effects of more advanced text representations, and fix the image representation to a baseline spatial pyramid kernel [Lazebnik et al., 2009] over basic color, texture, and SIFT [Lowe, 2004; Vedaldi and Fulkerson, 2008] features.”