Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern

By Xianbiao Qi, Rong Xiao, Chun-Guang Li, Yu Qiao, Jun Guo, Xiaoou Tang. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014

338 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/4c14bbf57bdf7645ca0d9c86a76446bb42b129e4

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

In Media Technology

Citations in the corpus

Median Robust Extended Local Binary Pattern for Texture Classification (2016, methodology): “…LBP method has been successfully applied to many diverse problems including dynamic texture recognition, remote sensing, ﬁngerprint matching, visual inspection, image retrieval, biomedical image analysis, face image analysis, motion analysis, edge detection, and environment modeling [1], [7]–[11].”
Material recognition in the wild with the Materials in Context Database (2014, methodology): “FMD has been used in research on new features and learning methods for material perception and recognition [17, 10, 20, 25].”
On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization (2016, positive): “300visual words, resulting in a 1800 dimensional feature. 2) Pairwise rotation invariant co-occurrence local binary pattern (PRI-CoLBP)feature, which was proven to be suitable for scene classiﬁcation [43] . Different from other LBP variants, PRI-CoLBP not only captured the spatial context co-occurre”
Deep filter banks for texture recognition and segmentation (2015, neutral): “7 [33, 37] OS+R acc 39.”
Deep Filter Banks for Texture Recognition, Description, and Segmentation (2015, methodology): “ccuracy absolute improvement is more than 11% across the board. Compared to the state of the art, FV-SIFT is generally very competitive, outperforming the specialized texture descriptors developed by [83, 88] in FMD (and this without using ground-truth texture segmentations as used by [88]). Yet FV-”
Deep convolutional filter banks for texture recognition and segmentation (2014, neutral): “V FC+FV-VD (a) KTH-T2b acc 70.8 2.7 71 2.3 73.3 4.7 73.9 4.9 75.4 1.5 81.8 2.5 81.1 2.4 81.5 2.0 76.0 2.9 [40] FMD acc 59.8 1.6 70.3 1.8 73.5 2.0 76.6 1.9 77.4 1.8 79.8 1.8 82.4 1.5 82.2 1.4 57.7 1.7 [33,37] OS+R acc 39.8 41.3 52.5 54.9 43.4 59.5 60.9 58.7 – (b) DTD acc 58.6 1.2 58.8 0.866.8 1.6 69.”