TY - GEN
T1 - Ransp
T2 - 2020 IEEE International Conference on Multimedia and Expo, ICME 2020
AU - Zhu, Dandan
AU - Chen, Yongqing
AU - Han, Tian
AU - Zhao, Defang
AU - Zhu, Yucheng
AU - Zhou, Qiangqiang
AU - Zhai, Guangtao
AU - Yang, Xiaokang
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - Various convolutional neural network (CNN)-based methods have shown the ability to boost the performance of saliency prediction on omnidirectional images (ODIs). However, these methods are limited by sub-optimal accuracy, because not all the features extracted by the CNN model are not useful for the final fine-grained saliency prediction. Features are redundant and have negative impact on the final fine-grained saliency prediction. To tackle this problem, we propose a novel Ranking Attention Network for saliency prediction (RANSP) of head fixations on ODIs. Specifically, the part-guided attention (PA) module and channel-wise feature (CF) extraction module are integrated in a unified framework and are trained in an end-to-end manner for fine-grained saliency prediction. To better utilize the channel-wise feature map, we further propose a new Ranking Attention Module (RAM), which automatically ranks and selects these maps based on scores for fine-grained saliency prediction. Extensive experiments are conducted to show the effectiveness of our method for saliency prediction of ODIs.
AB - Various convolutional neural network (CNN)-based methods have shown the ability to boost the performance of saliency prediction on omnidirectional images (ODIs). However, these methods are limited by sub-optimal accuracy, because not all the features extracted by the CNN model are not useful for the final fine-grained saliency prediction. Features are redundant and have negative impact on the final fine-grained saliency prediction. To tackle this problem, we propose a novel Ranking Attention Network for saliency prediction (RANSP) of head fixations on ODIs. Specifically, the part-guided attention (PA) module and channel-wise feature (CF) extraction module are integrated in a unified framework and are trained in an end-to-end manner for fine-grained saliency prediction. To better utilize the channel-wise feature map, we further propose a new Ranking Attention Module (RAM), which automatically ranks and selects these maps based on scores for fine-grained saliency prediction. Extensive experiments are conducted to show the effectiveness of our method for saliency prediction of ODIs.
KW - Channel-wise feature map
KW - Omnidirectional images
KW - Part-guided attention
KW - Ranking attention
KW - Saliency prediction
UR - http://www.scopus.com/inward/record.url?scp=85090389811&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090389811&partnerID=8YFLogxK
U2 - 10.1109/ICME46284.2020.9102867
DO - 10.1109/ICME46284.2020.9102867
M3 - Conference contribution
AN - SCOPUS:85090389811
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - 2020 IEEE International Conference on Multimedia and Expo, ICME 2020
Y2 - 6 July 2020 through 10 July 2020
ER -