Multi-task low-rank affinity pursuit for image segmentation

By Bin Cheng, Guangcan Liu, Jingdong Wang, Zhongyang Huang, Shuicheng Yan. 2011

220 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

1. Xiaochun Cao
2. Huan Fu
3. Changqing Zhang
4. Shuicheng Yan
5. Ju Sun
6. Qiang Yang
7. Jianfei Cai
8. Fanman Meng

In Computational Mechanics

1. Zhouchen Lin
2. Shuicheng Yan
3. Xiaochun Cao
4. Changqing Zhang
5. Qiang Yang
6. Huan Fu
7. Yu Zhang
8. Ivica Kopriva

In Computer Vision and Pattern Recognition

1. Xiaochun Cao
2. Shuicheng Yan
3. Zhouchen Lin
4. Dacheng Tao
5. Huan Fu
6. Changqing Zhang
7. Qiang Yang
8. Luc Van Gool

Citations in the corpus

• An Overview of Multi-task Learning (2018, neutral): “Applications of MTL based on non-facial images include object categorization [86], image segmentation [89,90], identifying brain imaging predictors [91], saliency detection [92], action recognition [93], scene classification [94], multi-attribute prediction [95], multi-camera person re-identificatio”
• A Survey on Multi-Task Learning (2017, background): “Feature Selection Face and object recognition [211] siRNA efficacy prediction [212] Microblog analysis [119] Behavioral targeting [213] Brain imaging [214] Genetic marker detection [215] Mental state examination [216] Predict cognitive outcome [217] Survival analysis [120] Genetic trait prediction [”
• Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, background): “Moreover, the affinity matrix can also be learned by using the recent multi-task low-rank representation algorithm presented in [46].”
• Robust Recovery of Subspace Structures by Low-Rank Representation (2010, methodology): “In summary, the contributio ns of this work include: • We develop a simple yet effective method, termed LRR, which has been used to achieve state-of-the-art performance in several applications such as motion segmentation [4], image segmentation [18], saliency detection [19] and face recognition [4].”
• Graph-Regularized Low-Rank Representation for Destriping of Hyperspectral Images (2013, unknown): “More recently, low-rank representation (LRR) [24] as a subspace recovery technique has been successfully applied in several areas of image processing [25]–[28].”
• Multi-view low-rank sparse subspace clustering (2017, background): “Previous multi-view subspace clustering works [42, 43, 44, 45] address the problem by constructing affinity matrix on each view separately and then extend algorithm to handle multi-view data.”
• Low-Rank Tensor Constrained Multiview Subspace Clustering (2015, background): “,E ) to have jointly consistent magnitude values, and the effectiveness of which has been widely proved [8].”
• Diversity-induced Multi-view Subspace Clustering (2015, methodology): “, sparse subspace clustering (SSC) [10], low-rank representation segmentation (LRR) [18] and smooth representation clustering (SMR) [15]), and be employed in numerous research areas, including face clustering [29, 32], image segmentation[7], and medical image analysis [11].”