Robust visual tracking via multi-task sparse learning

By Tianzhu Zhang, Bernard Ghanem, Si Liu, Narendra Ahuja. 2012

724 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

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 Electrical and Electronic Engineering

Citations in the corpus

A Survey on Multi-Task Learning (2017, methodology): “In [170], [171], a multi-task dictionary is learned for visual tracking via the `p,1 sparsity.”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, methodology): “Various generative target appearance modeling algorithms have been proposed including sparse representation [31, 43], density estimation [16, 22], and incremental subspace learning [32].”
Transfer Learning Based Visual Tracking with Gaussian Processes Regression (2014, methodology): “These trackers include Struck [8], SCM [45], TLD [15], ASLA [14], VTD [17], VTS [18], CXT [4], LSK [24], CSK [10], MTT [44] and LOT [27].”
Learning deep features for multiple object tracking by using a multi-task learning strategy (2014, background): “Multi-task learning [11, 32, 33, 34, 35, 36, 37] has been proven to be more effective than single task learning as multiple tasks are learned simultaneously rather than independently.”
Online Multi-Expert Learning for Visual Tracking (2020, background): “Existing trackers can be categorized as discriminative or generative methods [18], [26]–[31].”
Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables (2019, background): “, image classification [15, 33, 32, 31], object detection [9], or object tracking [38, 19]), of which the loss functions are factorized to independent (i.”
A Survey of Sparse Representation: Algorithms and Applications (2015, methodology): “[205] employed the concept of sparse representation based on a particle filter framewor k t construct a multi-task sparse learning method denoted as multi-task tracking for robust visual tracking.”
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015, methodology): “…the target appearance model, various approaches have been proposed including sparse representation (Bao et al., 2012; Jia et al., 2012; Mei & Ling, 2009; Zhang et al., 2012; Zhong et al., 2012), online density estimation (Han et al., 2008), incremental subspace learning (Ross et al., 2004), etc.”
Learning a Deep Compact Image Representation for Visual Tracking (2013, methodology): “All trackers except MTT can track the object but CT and MIL do not support scale change and hence the results are less satisfactory.”
Learning Collaborative Sparse Representation for Grayscale-Thermal Tracking (2016, methodology): “[14] constructed a multi-task sparse learning method denoted as multi-task”
Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, methodology): “A preliminary conference version of this work can be referred to in Zhang et al. (2012b).”
Hedged Deep Tracking (2016, background): “Most existing tracking approaches focus on either designing effective decision models [13, 12, 16, 40] or extracting effective features [6, 24, 41, 1].”
Multi-task Correlation Particle Filter for Robust Object Tracking (2017, methodology): “To solve (3), we use the Accelerated Proximal Gradient method, which has been widely used to efficiently solve convex optimization problems with non-smooth terms [42, 43].”
Robust Object Tracking via Sparse Collaborative Appearance Model (2014, background): “The optimal state is obtained by the maximum a posteriori estimation (MAP) over a set of N samples, x̂t = argxit max p(zt |x i t )p(x i t |xt−1), (3) where xit is the i -th sample at frame t .”
Visual Tracking via Locality Sensitive Histograms (2013, background): “For presentation clarity, we only show the results by the trackers with the top average success rate, i.e., CT [27], MIL [2], TLD [11], Struck [8], DFT [19] and MTT [28] .”
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].”