Beyond Holistic Object Recognition: Enriching Image Understanding with Part States
Abstract
Important high-level vision tasks require rich semantic descriptions of objects at part level. Based upon previous work on part localization, in this paper, we address the problem of inferring rich semantics imparted by an object part in still images. Specifically, we propose to tokenize the semantic space as a discrete set of part states. Our modeling of part state is spatially localized, therefore, we formulate the part state inference problem as a pixel-wise annotation problem. An iterative part-state inference neural network that is efficient in time and accurate in performance is specifically designed for this task. Extensive experiments demonstrate that the proposed method can effectively predict the semantic states of parts and simultaneously improve part segmentation, thus benefiting a number of visual understanding applications. The other contribution of this paper is our part state dataset which contains rich part-level semantic annotations.
Cite
Text
Lu et al. "Beyond Holistic Object Recognition: Enriching Image Understanding with Part States." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00727Markdown
[Lu et al. "Beyond Holistic Object Recognition: Enriching Image Understanding with Part States." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/lu2018cvpr-beyond/) doi:10.1109/CVPR.2018.00727BibTeX
@inproceedings{lu2018cvpr-beyond,
title = {{Beyond Holistic Object Recognition: Enriching Image Understanding with Part States}},
author = {Lu, Cewu and Su, Hao and Li, Yonglu and Lu, Yongyi and Yi, Li and Tang, Chi-Keung and Guibas, Leonidas J.},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00727},
url = {https://mlanthology.org/cvpr/2018/lu2018cvpr-beyond/}
}