Interactive deep learning method for segmenting moving objects

By Yi Wang, Zhiming Luo, Pierre-Marc Jodoin. Pattern Recognition Letters, 2017

317 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation (2018, methodology): “orrespondingweights are randomlyinitialized. Leaky ReLU functions are employed as activation functions. Experimental results on CDnet 2014 datasets showsthatBScGAN outperformsConvNets[22],CascadedCNN [204],and Deep CNN [4] with an an average F-Measure of 0.9763without the category PTZ. Zheng et al. ”
Background Subtraction in Real Applications: Challenges, Current Models and Future Directions (2019, methodology): “In addition, research focus on future directions with background subtraction methods with mathematical models, machine learning models, signal processing models and classification models: 1) statistical models [287][242][232][8], fuzzy models [25][26] and Dempsterschafer models [259] for mathematica”
Online Adaptation of Convolutional Neural Networks for Video Object Segmentation (2017, background): “Recently, deep learning based approaches, which often utilize large classiﬁcation datasets for pretraining, have shown extremely good performance for VOS [7, 20, 24, 35] and the related tasks of single-object tracking [5, 18, 31] and background modeling [2, 6, 44].”