·1160· 智能系统学报 第14卷 的引入导致网络实时处理能力下降，如何同时提 [12]REN Zhixiang,GAO Shenghua,CHIA L T,et al.Region 高预测效果和实时处理能力值得进一步研究。 based saliency detection and its application in object re- 参考文献： cognition[J].IEEE transactions on circuits and systems for video technology,2014,24(5):769-779 [1]ACHANTA R,HEMAMI S,ESTRADA F,et al.Fre- [13]MU Nana,XU Xiaolong,ZHANG Xong,et al.Salient ob- quency-tuned salient region detection[C]//Proceedings of ject detection using a covariance-based CNN model in 2009 IEEE Conference on Computer Vision and Pattern low-contrast images[J].Neural computing and applica- Recognition.Miami,USA,2009:1597-1604. tions.2018,298):181-192 [2]RONNEBERGER O.FISCHER P.BROX T.U-Net:con- [14]ZHOU Li,YANG Zhaohui,ZHOU Zongtan,et al.Sali- volutional networks for biomedical image segmentation ent region detection using diffusion process on a two-lay- [J.arXiv:1505.04597,2015. er sparse graph[J].IEEE transactions on image pro- [3]ITTI L,KOCH C.NIEBUR E.A model of saliency-based cessing,2017,26(12:5882-5894. visual attention for rapid scene analysis[J].IEEE transac- [15]LIU Tie,DUAN Haibin,SHANG Yuanyuan,et al.Auto- tions on pattern analysis and machine intelligence,1998, matic salient object sequence rebuilding for video seg- 20(11):12541259 ment analysis[J].Science China information sciences, [4]LIU Tie,ZHENG Nanning,DING Wei,et al.Video atten- 2018,61(1:012205. tion:learning to detect a salient object sequence[C]/Pro- [16]ZHANG Jing,FENG Shengwei,LI Da,et al.Image re- ceedings of 200819th International Conference on Pattern trieval using the extended salient region[J].Information Recognition.Tampa,USA,2008:1-4. sciences.2017,399:154-182 [5]LI Guanbin,YU Yizhou.Visual saliency based on [17]SINGH C,PREET KAUR K.A fast and efficient image multiscale deep features[J].Computer science,2015. retrieval system based on color and texture features[]]. [6]WANG Lijun,LU Huchuan,RUAN Xiang,et al.Deep net- Journal of visual communication and image representa- works for saliency detection via local estimation and glob- tion,2016,41:225-238 al search[C]//Proceedings of 2015 IEEE Conference on [18]XU Gongwen,XU Lina,LI Xiaomei,et al.An image re- Computer Vision and Pattern Recognition.Boston,USA, 2015:3183-3192 trieval method based on visual dictionary and saliency re- gion[J].International journal of signal processing,image [7]WANG Linzhao,WANG Lijun,LU Huchuan,et al.Sali- ent object detection with recurrent fully convolutional net- processing and pattern recognition,2016,9(7):263-274. works[J].IEEE transactions on pattern analysis and ma- [19]ZHAO Rui,OUYANG Wanli,LI Hongsheng,et al.Sali- chine intelligence,2018,41(7):1734-1746. ency detection by multi-context deep learning[C]//Pro- [8]CHENG Mingming,ZHANG Guoxin,MITRA N,et al. ceedings of 2015 IEEE Conference on Computer Vision Global contrast based salient region detection[Cl//Proceed- and Pattern Recognition.Boston,USA,2015:1265-1274. ings of 2011 IEEE Conference on Computer Vision and [20]DAI Jifeng,HE Kaiming,LI Yi,et al.Instance-sensitive Pattern Recognition.Colorado Springs,USA,2011: fully convolutional networks[J].Computer science,2016. 409-416. [21]YANG Wei,OUYANG Wanli,LI Hongsheng,et al.End- [9]JIANG Zhuolin,DAVIS L S.Submodular salient region to-end learning of deformable mixture of parts and deep detection[C]//Proceedings of 2013 IEEE Conference on convolutional neural networks for human pose estimation Computer Vision and Pattern Recognition.Portland,USA, [C]//Proceedings of 2016 IEEE Conference on Computer 2013:2043-2050. Vision and Pattern Recognition.Las Vegas,USA,2016 [10]JUNG C.KIM C.A unified spectral-domain approach for 3073-3082. saliency detection and its application to automatic object [22]HARIHARAN B,ARBELAEZ P,GIRSHICK R,et al. segmentation[J].IEEE transactions on image processing Hypercolumns for object segmentation and fine-grained 2012.21(3:1272-1283 localization[C]//Proceedings of 2015 IEEE Conference on [11]BADRINARAYANAN V,KENDALL A,CIPOLLA R. Computer Vision and Pattern Recognition.Boston,USA. SegNet:a deep convolutional encoder-decoder architec- 2015:447-456 ture for image segmentation[J.Computer science,arXiv: [23]LEE G,TAI Y W,KIM J.Deep saliency with encoded 1511.00561.2015. low level distance map and high level features[C]//Pro-的引入导致网络实时处理能力下降，如何同时提 高预测效果和实时处理能力值得进一步研究。 参考文献： ACHANTA R, HEMAMI S, ESTRADA F, et al. Fre￾quency-tuned salient region detection[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 1597–1604. [1] RONNEBERGER O, FISCHER P, BROX T. U-Net: con￾volutional networks for biomedical image segmentation [J]. arXiv: 1505.04597, 2015. [2] ITTI L, KOCH C, NIEBUR E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE transac￾tions on pattern analysis and machine intelligence, 1998, 20(11): 1254–1259. [3] LIU Tie, ZHENG Nanning, DING Wei, et al. Video atten￾tion: learning to detect a salient object sequence[C]/Pro￾ceedings of 200819th International Conference on Pattern Recognition. Tampa, USA, 2008: 1–4. [4] LI Guanbin, YU Yizhou. Visual saliency based on multiscale deep features[J]. Computer science, 2015. [5] WANG Lijun, LU Huchuan, RUAN Xiang, et al. Deep net￾works for saliency detection via local estimation and glob￾al search[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015: 3183–3192. [6] WANG Linzhao, WANG Lijun, LU Huchuan, et al. Sali￾ent object detection with recurrent fully convolutional net￾works[J]. IEEE transactions on pattern analysis and ma￾chine intelligence, 2018, 41(7): 1734–1746. [7] CHENG Mingming, ZHANG Guoxin, MITRA N, et al. Global contrast based salient region detection[C]//Proceed￾ings of 2011 IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs, USA, 2011: 409–416. [8] JIANG Zhuolin, DAVIS L S. Submodular salient region detection[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 2043–2050. [9] JUNG C, KIM C. A unified spectral-domain approach for saliency detection and its application to automatic object segmentation[J]. IEEE transactions on image processing, 2012, 21(3): 1272–1283. [10] BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architec￾ture for image segmentation[J]. Computer science, arXiv: 1511.00561, 2015. [11] REN Zhixiang, GAO Shenghua, CHIA L T, et al. Region￾based saliency detection and its application in object re￾cognition[J]. IEEE transactions on circuits and systems for video technology, 2014, 24(5): 769–779. [12] MU Nana, XU Xiaolong, ZHANG Xong, et al. Salient ob￾ject detection using a covariance-based CNN model in low-contrast images[J]. Neural computing and applica￾tions, 2018, 29(8): 181–192. [13] ZHOU Li, YANG Zhaohui, ZHOU Zongtan, et al. Sali￾ent region detection using diffusion process on a two-lay￾er sparse graph[J]. IEEE transactions on image pro￾cessing, 2017, 26(12): 5882–5894. [14] LIU Tie, DUAN Haibin, SHANG Yuanyuan, et al. Auto￾matic salient object sequence rebuilding for video seg￾ment analysis[J]. Science China information sciences, 2018, 61(1): 012205. [15] ZHANG Jing, FENG Shengwei, LI Da, et al. Image re￾trieval using the extended salient region[J]. Information sciences, 2017, 399: 154–182. [16] SINGH C, PREET KAUR K. A fast and efficient image retrieval system based on color and texture features[J]. Journal of visual communication and image representa￾tion, 2016, 41: 225–238. [17] XU Gongwen, XU Lina, LI Xiaomei, et al. An image re￾trieval method based on visual dictionary and saliency re￾gion[J]. International journal of signal processing, image processing and pattern recognition, 2016, 9(7): 263–274. [18] ZHAO Rui, OUYANG Wanli, LI Hongsheng, et al. Sali￾ency detection by multi-context deep learning[C]//Pro￾ceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015: 1265–1274. [19] DAI Jifeng, HE Kaiming, LI Yi, et al. Instance-sensitive fully convolutional networks[J]. Computer science, 2016. [20] YANG Wei, OUYANG Wanli, LI Hongsheng, et al. End￾to-end learning of deformable mixture of parts and deep convolutional neural networks for human pose estimation [C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 3073–3082. [21] HARIHARAN B, ARBELÁEZ P, GIRSHICK R, et al. Hypercolumns for object segmentation and fine-grained localization[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015: 447–456. [22] LEE G, TAI Y W, KIM J. Deep saliency with encoded low level distance map and high level features[C]//Pro- [23] ·1160· 智 能 系 统 学 报 第 14 卷