Visual classification with multi-task joint sparse representation

By Xiao-Tong Yuan, Shuicheng Yan. 2010

324 citations recorded by the source corpus.

Subfields: 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 Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

An Overview of Multi-task Learning (2018, methodology): “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…”
A Survey on Multi-Task Learning (2017, methodology): “In [148], a multi-task feature selection model based on the `2,1 norm is proposed for multi-cue face recognition and object categorization.”
Tree-Guided Group Lasso for Multi-Task Regression with Structured Sparsity (2009, methodology): “Although our work is primarily motivated by eQTL mapping in genetics, the tree lasso is generally applicable to any multivariate-response regression problem, where the hierarchical group structure over the responses is given as desirable sources of structural bias, such as in many computer vision [Y”
Online Multi-Task Learning Framework for Ensemble Forecasting (2017, unknown): “Multi-task learning has been successfully used to solve multiple related learning problems in many applications, including computer vision [6], [7], healthcare [8], [9], recommender systems [10], [11], natural language processing [12] and genomics [13].”
Feature-based transfer learning with real-world applications (2010, background): “Applications of transfer learning in these fields include image classification [202, 158, 185, 218, 161, 94, 177], image retrieval [73, 115, 38], face verification from images [196], age estimation from facial images [225], image semantic segmentation [190], video retrieval [208, 73], video concept ”
Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition (2013, methodology): “For SR, LPP with SR, and GSR we use minimum reconstruction error [31] for classification.”
Image classification by non-negative sparse coding, low-rank and sparse decomposition (2011, methodology): “Some [6-8, 19, 21] tried to use the training samples as the bases directly.”
Robust visual tracking via multi-task sparse learning (2012, background): “It capitalizes on shared information between related tasks to improve the performance of each individual task, and it has been successfully applied to vision problems such as image classification [21] and image annotation [18].”
Sharing features between objects and their attributes (2011, background): “The focus has been on inter-class transfer between objects [10, 5, 22, 20], and jointly training detectors so that features are shared across objects [23, 3, 29], which lends to better efficiency during detection.”
Enhanced representation and multi-task learning for image annotation (2013, background): “Saliency in [4] is linked to inverse frequency of occurence and equally frequent edges are assigned the same saliency value.”
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 Sparse Learning with Beta Process Prior for Action Recognition (2013, methodology): “It capitalizes on shared information between related tasks to improve the performance of individual tasks, and it has been successfully applied to vision problems such as image classification [10], image annotation [3], and object tracking [4].”
Learning active facial patches for expression analysis (2012, background): “Yuan [28] developed a visual classification algorithm by learning the shared parts among different representation tasks.”
Sparse coding based visual tracking: Review and experimental comparison (2013, background): “A possible solution is to use multi-task sparse coding [69] to treat them as different tasks and then integrate them together.”
Unsupervised feature selection by regularized self-representation (2015, unknown): “Group sparsity, which is often used in multi-task learning [20] and joint representation [21], has also been applied to feature selection.”
Tracking via Robust Multi-task Multi-view Joint Sparse Representation (2013, methodology): “Inspired by previous works [33][35], the dependencies of these views as well as the intrinsic relationship of sampled particles should be jointly considered.”