深度学习从入门到放弃之CV-Visual tracking目录

根据github foolwood总结,Visual tracking可以分为两大分支:CNN和相关滤波。

CNN目前还未占领Tracking,一方面是因为CNN的模型目前处理image都无法实时性,另一方面是Video存在大量的冗余信息。CVPR2017/ICCV2017以及其他顶会,还是以CF为基础,对算法尤其是高等数学理论要求太高。



2010----MOSSE----Visual Object Tracking using Adaptive Correlation Filters

2012----CSK----Exploiting the Circulant Structure of Tracking-by-detection with Kernels

2013 First paper----Learning a deep compact image representation for visual tracking

2013----Online Object Tracking-A Benchmark

2014----ASMS----Robust scale-adaptive mean-shift for tracking

2014--Winner VOT2014----Accurate Scale Estimation for Robust Visual Tracking

2015----An Experimental Survey on Correlation Filter-based Tracking

2015----DeepSRDCF----Convolutional Features for Correlation Filter Based Visual Tracking

2015----KCF-DCF----High-Speed Tracking with Kernelized Correlation Filters

2015----MDNet----Winner VOT2015----Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

2015----Object Tracking Benchmark

2015----SO-DLT----Transferring Rich Feature Hierarchies for Robust Visual Tracking

2015----SRDCF----Learning Spatially Regularized Correlation Filters for Visual Tracking

2016----C-COT----Beyond Correlation Filters_Learning Continuous Convolution Operators for Visual Tracking

2016----TCNN----Winner VOT2016----Modeling and Propagating CNNs in a Tree Structure for Visual Tracking

2017----ADnet----Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning

2017----Attentional Correlation Filter Network for Adaptive Visual Tracking

2017----CACF----Context-Aware Correlation Filter Tracking

2017----CFNet----End-to-end representation learning for Correlation Filter based tracking

2017----ECO_Efficient Convolution Operators for Tracking

2017----Large Margin Object Tracking with Circulant Feature Maps

2017----Multi-task Correlation Particle Filter for Robust Object Tracking

2017----SANet_Structure-Aware Network for Visual Tracking


返回CV总目录

编辑于 2017-11-20

文章被以下专栏收录