Revisiting Jump-Diffusion Process for Visual Tracking: A Reinforcement Learning Approach | Zendy

Xiaobai Liu | Zendy; Qian Xu | Zendy; Thuan Chau | Zendy; Yadong Mu | Zendy; Lei Zhu | Zendy; Shuicheng Yan | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Revisiting Jump-Diffusion Process for Visual Tracking: A Reinforcement Learning Approach

Author(s) -

Xiaobai Liu,

Qian Xu,

Thuan Chau,

Yadong Mu,

Lei Zhu,

Shuicheng Yan

Publication year - 2018

Publication title -

ieee transactions on circuits and systems for video technology

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.873

H-Index - 168

eISSN - 1558-2205

pISSN - 1051-8215

DOI - 10.1109/tcsvt.2018.2862891

Subject(s) - computer science , visibility , artificial intelligence , jump , computer vision , jump diffusion , reinforcement learning , tracking (education) , markov process , process (computing) , set (abstract data type) , markov decision process , hidden markov model , object (grammar) , eye tracking , jump process , mathematics , statistics , psychology , pedagogy , physics , quantum mechanics , operating system , optics , programming language

In this paper, we revisit the classical stochastic jump-diffusion process and develop an effective variant for estimating visibility statuses of objects while tracking them in videos. Dealing with partial or full occlusions is a long standing problem in computer vision but largely remains unsolved. In this paper, we cast the above problem as a Markov decision process and develop a policy-based jum...

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research