Visual Classification With Multitask Joint Sparse Representation

By Xiao-Tong Yuan, Xiaobai Liu, Shuicheng Yan. 2012

410 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “Same is used in [30] as a generalization of L 1 norm in a multitask joint sparsity representation model to fuse complementary visual features across recognition tasks.”
Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach (2018, methodology): “SRC has been also applied to signal classification [8], visual tracking [15], and visual classification [26], etc.”
Forecasting Interactive Dynamics of Pedestrians with Fictitious Play (2016, methodology): “We train all three top layer classifiers jointly, as previous work has shown that multi-task learning helps to constrain the parameter learning [39, 47].”
CLRS: Continual Learning Benchmark for Remote Sensing Image Scene Classification (2020, methodology): “Finally, we compared the performance of multitask joint training, namely, we used Cumulative training [38] (the current batch data are mixed with all previous ones for training) as the baseline for evaluating the difficulty of a sequential batch.”
Visual Classification by ℓ1-Hypergraph Modeling (2015, methodology): “In comparison with the conventional neighborhoodbased hypergraph learning methods, the proposed method can refine the samples selected by KNN and thus noisy data can be removed.”
Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, background): “Multi-task learning has proven eﬀective in many computer vision problems [36,37].”
Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification (2014, methodology): “Features NSC SVM (Gehler and Nowozin 2009) MTJSRC-CG (Yuan and Yan 2010) SRC COPAR JDL FDDL”
Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, background): “Because of its promising performance in uncovering latent relationships among tasks, MTL has been widely used in machine learning [1], [2] and computer vision [3], [4] tasks.”
Overcoming Long-Term Catastrophic Forgetting Through Adversarial Neural Pruning and Synaptic Consolidation (2019, methodology): “We defined a multitask joint training with SGD (Joint) [34] as the baseline for evaluating the difficulty of a sequential task.”
Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, methodology): “It capitalizes on shared information between related tasks to improve the performance of each individual task, and it has been successfully applied to popular vision problems such as image classification [(Yuan and Yan 2010) and image annotation (Quattoni et al. 2009].”
Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, methodology): “It has been widely applied to machine learning [2, 44] and computer vision [45, 24].”