Discriminative local binary patterns for human detection in personal album

By Yadong Mu, Shuicheng Yan, Yi Liu, Thomas S. Huang, Bingfeng Zhou. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

332 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cf5feccca7eeed4929a5cd75078cc5fa4936e196

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

1. Xiaogang Wang
2. Luc Van Gool
3. Yi Yang
4. Dacheng Tao
5. Ling Shao
6. Qi Tian
7. Ming-Hsuan Yang
8. Alan L. Yuille

Citations in the corpus

• An HOG-LBP human detector with partial occlusion handling (2009, unknown): “As shown in Figure 6(a) in the experiments section, the detection results based on our cell-structured LBP are much better than [20].”
• Group-Wise Learning for Aurora Image Classification With Multiple Representations (2019, unknown): “1) Local Binary Pattern: Image representations based on LBP have been broadly used for texture classification [10], face recognition [29], and object detection [20], due to its simplicity and efficiency.”
• Human detection from images and videos: A survey (2016, background): “2 Appearance Features To compensate for the limitation of the edge-based features, appearance features computed from image intensity [127, 88, 108] or colour [124, 160] have been proposed.”
• Feature representation for statistical-learning-based object detection: A review (2015, background): “Categories Typical feature representation methods Engineering -based features Gradient features SIFT [2], PCA-SIFT(1) [3], RIFT [4], GLOH(1) [5], SURF [6], DAISY [7], GIST(1) [8], RIFF [9], WLD [10], HOG [11][12], integral histogram [13], v-HoG [14][15], CoHOG [16], spHOG [17], PQ-HOG [18], WHO(1) [”
• Local binary features for texture classification: Taxonomy and experimental study (2017, background): “With similar motivations as the heuristically designed LBP variants (Section 2.4.1), researchers seek to learn the most reliable and discriminative dominant patterns; representative work along this line includes DLBP [3], disLBP [80], LDRICoLBP [81] and ABLBP [82].”
• Human detection using partial least squares analysis (2009, background): “[17] propose a variation of local binary patterns to overcome some drawbacks of HOG, such as lack of color information.”
• Learning LBP structure by maximizing the conditional mutual information (2015, background): “Potentially, the proposed approach could handle a large set of binarized pixel differences, whereas approaches that directly extract features from the histogram bins [3, 8, 31, 32, 43–45] cannot as it is not feasible to enumerate 2 bins for a large n.”
• Recent advances and trends in visual tracking: A review (2011, background): “In Mu et al. [42], proposed two variants of LBP: Semantic-LBP and Fourier LBP.”