TY - GEN
T1 - High-level semantic feature for 3D shape based on deep belief networks
AU - Liu, Zhenbao
AU - Chen, Shaoguang
AU - Bu, Shuhui
AU - Li, Ke
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/9/3
Y1 - 2014/9/3
N2 - Deep learning has emerged as a powerful technique to extract high-level features from low-level information, which shows that hierarchical representation can be easily achieved. However, applying deep learning into 3D shape is still a challenge. In this paper, we propose a novel high-level feature learning method for 3D shape retrieval based on deep learning. In this framework, the low-level 3D shape descriptors are first encoded into visual bag-of-words, and then highlevel shape features are generated via deep belief network, which facilitates a good semantic preserving ability for the tasks of shape classification and retrieval. Experiments on 3D shape recognition and retrieval demonstrate the superior performance of the proposed method in comparison to the state-of-the-art methods.
AB - Deep learning has emerged as a powerful technique to extract high-level features from low-level information, which shows that hierarchical representation can be easily achieved. However, applying deep learning into 3D shape is still a challenge. In this paper, we propose a novel high-level feature learning method for 3D shape retrieval based on deep learning. In this framework, the low-level 3D shape descriptors are first encoded into visual bag-of-words, and then highlevel shape features are generated via deep belief network, which facilitates a good semantic preserving ability for the tasks of shape classification and retrieval. Experiments on 3D shape recognition and retrieval demonstrate the superior performance of the proposed method in comparison to the state-of-the-art methods.
KW - 3D Shape classification
KW - 3D shape retrieval
KW - Bag-of-words
KW - Deep belief networks
KW - Deep learning
UR - https://www.scopus.com/pages/publications/84908383843
U2 - 10.1109/ICME.2014.6890145
DO - 10.1109/ICME.2014.6890145
M3 - 会议稿件
AN - SCOPUS:84908383843
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - 2014 IEEE International Conference on Multimedia and Expo, ICME 2014
PB - IEEE Computer Society
T2 - 2014 IEEE International Conference on Multimedia and Expo, ICME 2014
Y2 - 14 July 2014 through 18 July 2014
ER -