@inproceedings{2b4e28e3c92b4685962f11220c5bee1c,
title = "Saliency detection with multi-contextual models and spatially coherent loss function",
abstract = "We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training phase and a refinement phase to increase the efficiency of the network.",
keywords = "Deep learning, Multi-contextual model, Saliency detection",
author = "Huang, {Po Sheng} and Shen, {Chin Han} and Hsu-Feng Hsiao",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE; 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 ; Conference date: 26-05-2019 Through 29-05-2019",
year = "2019",
doi = "10.1109/ISCAS.2019.8702378",
language = "American English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",
address = "United States",
}