Attribute prediction with long-range interactions via path coding
Lists
Only you see this
Abstract
Due to the describable or human-nameable nature of visual attributes, the appropriate utilization of attributes has been receiving much attention in recent years in many applications. Motivated by the assumption that the long-range interactions between attributes can boost image understanding and classification, path coding is utilized in this paper to model the long-range interactions between attributes for the attribute prediction, we call it attribute prediction via a path coding penalty (abbreviated as AP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CP). AP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CP not only introduces structured sparsity penalties over paths on a directed acyclic graph, but also captures the intrinsical long-range dependent interactions between attributes. The proposed AP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CP can be efficiently solved by leveraging network flow optimization. The experiments show that the proposed AP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CP achieves a better performance in attribute prediction.
BibTeX
@inproceedings{wang2014attribute,
author = {Zhuhao Wang and Fei Wu and Yahong Han and Jiebo Luo and Qi Tian and Yueting Zhuang},
title = {{Attribute prediction with long-range interactions via path coding}},
booktitle = {ICIP},
year = {2014},
doi = {10.1109/icip.2014.7026056},
}Loading related content...