@inproceedings{3ed800722bf44238b0cd49a6c5e21b21,
title = "Video pose estimation via medium granularity graphical model with spatial-temporal symmetric constraint part model",
abstract = "We address the problem of full body human pose estimation in video. Most previous work consider body part, pose or trajectory of body part as basic unit to compose the pose sequence. In contrast, we consider tracklet of body part as the basic unit. Based on this medium granularity representation we develop a spatio-temporal graphical model to select an optimal tracklet for each part in each video segment. In our model, tracklet nodes of symmetric parts are coupled to one node to overcome the double counting problem. Through iterative spatial and temporal parsing, optimal solution is achieved in polynomial time. We apply our model on three publicly available datasets and show remarkable quantitative and qualitative improvements over the state-of-the-art approaches.",
keywords = "Graphical model, Hidden Markov model, Markov network, Pose estimation",
author = "Qingxuan Shi and Huijun Di and Yao Lu and Ming Qin and Xuedong Tian",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 23rd IEEE International Conference on Image Processing, ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",
year = "2016",
month = aug,
day = "3",
doi = "10.1109/ICIP.2016.7532568",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "1299--1303",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
address = "United States",
}