Contextual Hypergraph Modeling for Salient Object Detection

By Xi Li, Yao Li, Chunhua Shen, Anthony R. Dick, Anton van den Hengel. 2013

199 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

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

In Cognitive Neuroscience

1. Ming-Ming Cheng
2. Ali Borji
3. Ming-Hsuan Yang
4. Qibin Hou
5. Deng-Ping Fan
6. Huchuan Lu
7. Haibin Ling
8. Huaizu Jiang

In Computer Vision and Pattern Recognition

1. Ming-Ming Cheng
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Luc Van Gool
5. Huchuan Lu
6. Yi Yang
7. Ling Shao
8. Xiaogang Wang

In Human-Computer Interaction

1. Ming-Ming Cheng
2. Haibin Ling
3. Ali Borji
4. Ming-Hsuan Yang
5. Qibin Hou
6. Philip H. S. Torr
7. Jia Li
8. S. Maybank

Citations in the corpus

• Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “, twice the mean values of S as in [51].”
• Cancer Diagnosis Using Deep Learning: A Bibliographic Review (2019, methodology): “There are many other methods for image segmentation: histogram thresholding, adaptive thresholding, gradient flow vector, distributed and localized region identification, clustering and statistical region growing [31], bootstrap learning [32], active contours, supervised learning, edge detection, fu”
• Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks (2017, background): “Both ROC and PR curves have been widely used for object detection related problems on general images [54].”
• Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “ematical formulation, computing the center-surround divergence based on feature statistics [18]. A cost-sensitive SVM is trained to measure the separability of a center region w.r.t. its surroundings [30]. The uniqueness can also be captured in a global scope by comparing a patch to its k nearest ne”
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection (2015, background): “These approaches detect the salient objects by computing the local center-surround differences [11], [19], [20], or evaluating the region uniqueness and rarity in the scene [21], [22], [23].”
• Object Detection With Deep Learning: A Review (2018, methodology): “The following approaches are evaluated: contextual hyper-graph modeling (CHM) [150], RC [151], discriminative regional feature integration (DRFI) [152], MC [138], multiscale deep CNN features (MDF) [146], local estimation and global search (LEGS) [136], DSR [149], multi-task deep neural network [141”
• RGBD Salient Object Detection: A Benchmark and Algorithms (2014, methodology): “To highlight the whole salient object, multi-scale contrast [29][44][27] and multi-cues integration [20,21] techniques are used.”
• Salient Object Detection: A Benchmark (2015, unknown): “ + C 140. 14 HS [77] CVPR 2013 EXE .528 15 GMR [78] CVPR 2013 M .149 16 DRFI [79] CVPR 2013 C .697 17 PCA [80] CVPR 2013 M + C 4.34 18 LBI [81] CVPR 2013 M + C 251. 19 GC [82] ICCV 2013 C .037 20 CHM [83] ICCV 2013 M + C 15.4 21 DSR [84] ICCV 2013 M + C 10.2 22 MC [85] ICCV 2013 M + C .195 23 UFO [8”
• Salient object detection: A survey (2014, background): “jectness, and focusness scores. Performance of salient object detection based on regions might be affected by the segmentation parameters. In addition to other approaches based on multi-scale regions [86,128,216], single-scale potential salient regions are extracted by solving the facility location ”
• Deeply Supervised Salient Object Detection with Short Connections (2016, methodology): “Four classical methods are also considered including RC [41], CHM [61], DSR [62], and DRFI [25], which have been proven to be the best in the benchmark study of Borji et al. [23].”