• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Higher-Order Conditional Random Field established with CNNs for Video Object Segmentation


Abstract

We perform the task of video object segmentation by incorporating a conditional random field (CRF) and convolutional neural networks (CNNs). Most methods employ a CRF to refine a coarse output from fully convolutional networks. Others treat the inference process of the CRF as a recurrent neural network and then combine CNNs and the CRF into an end-to-end model for video object segmentation. In contrast to these methods, we propose a novel higher-order CRF model to solve the problem of video object segmentation. Specifically, we use CNNs to establish a higher-order dependence among pixels, and this dependence can provide critical global information for a segmentation model to enhance the global consistency of segmentation. In general, the optimization of the higher-order energy is extremely difficult. To make the problem tractable, we decompose the higher-order energy into two parts by utilizing auxiliary variables and then solve it by using an iterative process. We conduct quantitative and qualitative analyses on multiple datasets, and the proposed method achieves competitive results.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
C. Hao, Y. Wang, B. Jiang, S. Liu and Z. Yang, "Higher-Order Conditional Random Field established with CNNs for Video Object Segmentation," KSII Transactions on Internet and Information Systems, vol. 15, no. 9, pp. 3204-3220, 2021. DOI: 10.3837/tiis.2021.09.007.

[ACM Style]
Chuanyan Hao, Yuqi Wang, Bo Jiang, Sijiang Liu, and Zhi-Xin Yang. 2021. Higher-Order Conditional Random Field established with CNNs for Video Object Segmentation. KSII Transactions on Internet and Information Systems, 15, 9, (2021), 3204-3220. DOI: 10.3837/tiis.2021.09.007.

[BibTeX Style]
@article{tiis:24930, title="Higher-Order Conditional Random Field established with CNNs for Video Object Segmentation", author="Chuanyan Hao and Yuqi Wang and Bo Jiang and Sijiang Liu and Zhi-Xin Yang and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2021.09.007}, volume={15}, number={9}, year="2021", month={September}, pages={3204-3220}}