• Home
  • Search
  • Visual object tracking with online sample selection via lasso regularization
  • Cite Icon25
  • https://doi.org/10.1007/s11760-016-1035-xCopy DOI Icon

Visual object tracking with online sample selection via lasso regularization

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In the past years, discriminative methods are popular in visual tracking. The main idea of the discriminative method is to learn a classifier to distinguish the target from the background. The key step is the update of the classifier. Usually, the tracked results are chosen as the positive samples to update the classifier, which results in the failure of the updating of the classifier when the tracked results are not accurate. After that the tracker will drift away from the target. Additionally, a large number of training samples would hinder the online updating of the classifier without an appropriate sample selection strategy. To address the drift problem, we propose a score function to predict the optimal candidate directly instead of learning a classifier. Furthermore, to solve the problem of a large number of training samples, we design a sparsity-constrained sample selection strategy to choose some representative support samples from the large number of training samples on the updating stage. To evaluate the effectiveness and robustness of the proposed method, we implement experiments on the object tracking benchmark and 12 challenging sequences. The experiment results demonstrate that our approach achieves promising performance.

Similar Papers
  • Research Article
  • Citations3

Predicting the seismic performance of large-scale dome structures with hybrid uncertainties based on Bayesian inference

  • Aug 01, 2024
  • Engineering Applications of Artificial Intelligence
  • Huidong Zhang +1
  • Research Article
  • Citations34

Semi-supervised deep learning for hyperspectral image classification

  • Jan 03, 2019
  • Remote Sensing Letters
  • Xudong Kang +2
  • Book Chapter
  • Citations2

Research on the Method of Tibetan Recognition Based on Component Location Information

  • Jan 01, 2018
  • Yuehui Han +3
  • Research Article
  • Citations83

Spectral Collaborative Representation based Classification for hand gestures recognition on electromyography signals

  • Sep 16, 2015
  • Biomedical Signal Processing and Control
  • Ali Boyali +1
  • Research Article
  • Citations8

LSTM guided ensemble correlation filter tracking with appearance model pool

  • Feb 25, 2020
  • Computer Vision and Image Understanding
  • Monika Jain +4
  • PDF
  • Research Article
  • Citations5

A Weak Sample Optimisation Method for Building Classification in a Semi-Supervised Deep Learning Framework

  • Sep 08, 2023
  • Remote Sensing
  • Yanjun Wang +5
  • Research Article
  • Citations115

Detection of the multivariate geochemical anomalies associated with mineralization using a deep convolutional neural network and a pixel-pair feature method

  • May 19, 2021
  • Applied Geochemistry
  • Chunjie Zhang +2
  • Research Article
  • Citations315

DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking.

  • Dec 22, 2015
  • IEEE Transactions on Image Processing
  • Hanxi Li +2
  • Research Article

Visual tracking with multilevel feature, similarity attention, color constraint, and global redetection

  • Sep 01, 2021
  • International Journal of Advanced Robotic Systems
  • Song Guiling +5
  • Supplementary Content

Person Re-identification and Tracking in Video Surveillance

  • Jun 16, 2020
  • University of Liverpool
  • Yanchun Xie
  • PDF
  • Research Article
  • Citations21

Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

  • Mar 04, 2021
  • International Journal of Automation and Computing
  • Xiao-Qin Zhang +5
  • Conference Article
  • Citations8

Transfer Learning in General Lensless Imaging through Scattering Media

  • Nov 09, 2020
  • Yukuan Yang +6
  • Research Article
  • Citations99

Scene Classification of High-Resolution Remotely Sensed Image Based on ResNet

  • Oct 10, 2019
  • Journal of Geovisualization and Spatial Analysis
  • Mingchang Wang +4
  • Conference Article
  • Citations4

Maximum classification optimization-based active learning for image classification

  • Oct 01, 2014
  • Zhengwei Cui +4
  • Conference Article
  • Citations44

Small sample size effects in statistical pattern recognition: recommendations for practitioners and open problems

  • Jun 16, 1990
  • S.J Raudys +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.