{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T09:16:01Z","timestamp":1693732561206},"reference-count":68,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1587\/transinf.2022edp7220","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T23:08:30Z","timestamp":1693523310000},"page":"1572-1583","source":"Crossref","is-referenced-by-count":0,"title":["Siamese Transformer for Saliency Prediction Based on Multi-Prior Enhancement and Cross-Modal Attention Collaboration"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Fazhan","family":"YANG","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingge","family":"GUO","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"LIANG","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peipei","family":"ZHAO","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanhua","family":"LI","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] R.A. Rensink, \u201cThe dynamic representation of scenes,\u201d Visual Cognit., vol.7, no.1-3, pp.17-42, 2000. 10.1080\/135062800394667","DOI":"10.1080\/135062800394667"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] H. Huang, M. Cai, L. Lin, L. Lin, J. Zheng, X. Mao, X. Qian, Z. Peng, J. Zhou, Y. Iwamoto, X.-H. Han, Y.-W. Chen, R. Tong, \u201cGraph-based pyramid global context reasoning with a saliency-aware projection for COVID-19 lung infections segmentation,\u201d ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021. 10.1109\/ICASSP39728.2021.9413957","DOI":"10.1109\/ICASSP39728.2021.9413957"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] S.K. Yarlagadda, D.M. Montserrat, D. G\u00fcera, C.J. Boushey, D.A. Kerr, and F. Zhu, \u201cSaliency-aware class-agnostic food image segmentation,\u201d ACM Trans. Comput., vol.2, no.3, pp.1-17, July 2021. 10.1145\/3440274","DOI":"10.1145\/3440274"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] L. Ye, Z. Liu, L. Li, L. Shen, C. Bai, and Y. Wang, \u201cSalient object segmentation via effective integration of saliency and objectness,\u201d IEEE Trans. Multimedia, vol.19, no.8, pp.1742-1756, Aug. 2017. 10.1109\/TMM.2017.2693022","DOI":"10.1109\/TMM.2017.2693022"},{"key":"5","unstructured":"[5] W. Wang, J. Shen, and F. Porikli, \u201cSaliency-aware geodesic video object segmentation,\u201d IEEE CVPR 2015, 2015. 10.1109\/CVPR.2015.7298961"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] H. Hadizadeh and I.V. Baji\u0107, \u201cSaliency-aware video compression,\u201d IEEE Trans. Image Process. : a Publication of the IEEE Signal Processing Society, vol.23, no.1, pp.19-33, Jan. 2014. 10.1109\/TIP.2013.2282897","DOI":"10.1109\/TIP.2013.2282897"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] Q.-G. Ji, Z.-D. Fang, Z.-H. Xie, and Z.-M. Lu, \u201cVideo abstraction based on the visual attention model and online clustering,\u201d Signal Process. Image Commun., vol.28, no.3, pp.241-253, March2013. 10.1016\/j.image.2012.11.008","DOI":"10.1016\/j.image.2012.11.008"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] Q. Jiang, S. Feng, W. Lin, K. Gu, G. Jiang, and H. Sun, \u201cOptimizing multistage discriminative dictionaries for blind image quality assessment,\u201d IEEE Trans. Multimedia, vol.20, no.8, pp.2035-2048, Aug. 2018. 10.1109\/TMM.2017.2763321","DOI":"10.1109\/TMM.2017.2763321"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] K. Gu, S. Wang, H. Yang, W. Lin, G. Zhai, X. Yang, and W. Zhang, \u201cSaliency-guided quality assessment of screen content images,\u201d IEEE Trans. Multimedia, vol.18, no.6, pp.1098-1110, June 2016. 10.1109\/TMM.2016.2547343","DOI":"10.1109\/TMM.2016.2547343"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] S. Goferman, L. Zelnik-Manor, and A. Tal, \u201cContext-aware saliency detection,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.34, no.10, pp.1915-1926, Oct. 2012. 10.1109\/TPAMI.2011.272","DOI":"10.1109\/TPAMI.2011.272"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Harel, C. Koch, and P. Perona, \u201cGraph-based visual saliency,\u201d Conference on Advances in Neural Information Processing Systems, 2006.","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] L. Itti, C. Koch, and E. Niebur, \u201cA model of saliency-based visual attention for rapid scene analysis,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.20, no.11, pp.1254-1259, Nov. 1998. 10.1109\/34.730558","DOI":"10.1109\/34.730558"},{"key":"13","unstructured":"[13] N. Bruce and J.K. Tsotsos, \u201cSaliency based on information maximization,\u201d International Conference on Neural Information Processing Systems, pp.155-162, Dec. 2005."},{"key":"14","unstructured":"[14] D. Gao and N. Vasconcelos, \u201cDiscriminant saliency for visual recognition from cluttered scenes,\u201d Advances in Neural Information Processing Systems 17, 2004."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] X. Hou and L. Zhang, \u201cSaliency detection: A spectral residual approach,\u201d IEEE Conference on Computer Vision and Pattern Recognition, 2007. 10.1109\/CVPR.2007.383267","DOI":"10.1109\/CVPR.2007.383267"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] G. Huang, Z. Liu, L. van der Maaten, and K.Q. Weinberger, \u201cDensely connected convolutional networks,\u201d IEEE Computer Society, 2016. 10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"18","unstructured":"[18] A. Krizhevsky, I. Sutskever, and G. Hinton, \u201cImageNet classification with deep convolutional neural networks,\u201d Advances in Neural Information Processing Systems, 2012."},{"key":"19","unstructured":"[19] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, L. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Computation and Language, arXiv, 2017. 10.48550\/arXiv.1706.03762"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, \u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] M.M. Cheng, G.X. Zhang, N.J. Mitra, X. Huang, and S.-M. Hu, \u201cGlobal contrast based salient region detection,\u201d Computer Vision and Pattern Recognition, 2011. 10.1109\/CVPR.2011.5995344","DOI":"10.1109\/CVPR.2011.5995344"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] E. Vig, M. Dorr, and D. Cox, \u201cLarge-scale optimization of hierarchical features for saliency prediction in natural images,\u201d 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. 10.1109\/CVPR.2014.358","DOI":"10.1109\/CVPR.2014.358"},{"key":"23","unstructured":"[23] M. K\u00fcmmerer, L. Theis, and M. Bethge, \u201cDeep Gaze I: Boosting saliency prediction with feature maps trained on ImageNet,\u201d Comput. Sci., 2014. 10.48550\/arXiv.1411.1045"},{"key":"24","unstructured":"[24] K. Simonyan and A. Zisserman, \u201cVery deep convolutional networks for large-scale image recognition,\u201d Comput. Sci., 2014. 10.48550\/arXiv.1409.1556"},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] S. Kruthiventi, K. Ayush, and R.V. Babu \u201cDeepFix: A fully convolutional neural network for predicting human eye fixations,\u201d IEEE Trans. Image Process., vol.26, no.9, pp.4446-4456, Sept. 2017. 10.1109\/TIP.2017.2710620","DOI":"10.1109\/TIP.2017.2710620"},{"key":"26","unstructured":"[26] J. Pan, C. Canton, K. McGuinness, N.E. O'Connor, J. Torres, E. Sayrol, and X. Giro-i-Nieto, \u201cSalGAN: Visual saliency prediction with generative adversarial networks,\u201d Computer Vision and Pattern Recognition, 2017. 10.48550\/arXiv.1701.01081"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] C. Marcella, B. Lorenzo, S. Giuseppe, and R. Cucchiara, \u201cPredicting human eye fixations via an LSTM-based saliency attentive model,\u201d IEEE Trans. Image Process., vol.27, no.10, pp.5142-5154, Oct. 2016. 10.1109\/TIP.2018.2851672","DOI":"10.1109\/TIP.2018.2851672"},{"key":"28","unstructured":"[28] S. Jia and N.D.B. Bruce, \u201cEML-NET:An expandable Multi-Layer NETwork for saliency prediction,\u201d Computer Vision and Pattern Recognition, arXiv, 2018. 10.48550\/arXiv.1805.01047"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] A. Linardos, M. K\u00fcmmerer, O. Press, and M. Bethge, \u201cDeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling,\u201d 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 10.1109\/ICCV48922.2021.01268","DOI":"10.1109\/ICCV48922.2021.01268"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] J. Lou, H. Lin, D. Marshall, D. Saupe, and H. Liu, \u201cTranSalNet: Towards perceptually relevant visual saliency prediction,\u201d Multimedia, arXiv e-prints, 2022. 10.48550\/arXiv.2110.03593","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"31","unstructured":"[31] N. Parmar, A. Vaswani, J. Uszkoreit, \u0141. Kaiser, N. Shazeer, A. Ku, and D. Tran, \u201cImage transformer,\u201d Computer Vision and Pattern Recognition, 2018. 10.48550\/arXiv.1802.05751"},{"key":"32","unstructured":"[32] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, \u201cAn image is worth 16x16 words: Transformers for image recognition at scale,\u201d International Conference on Learning Representations, 2021."},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, S. Zagoruyko, \u201cEnd-to-end object detection with transformers,\u201d ECCV, 2020. 10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] N. Liu, N. Zhang, K. Wan, L. Shao, and J. Han, \u201cVisual saliency transformer,\u201d Computer Vision and Pattern Recognition, arXiv, 2021. 10.48550\/arXiv.2104.12099","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"35","doi-asserted-by":"publisher","unstructured":"[35] Z. Liu, Y. Tan, Q. He, and Y. Xiao, \u201cSwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection,\u201d IEEE Trans. Circuits Syst. Video Technol., vol.32, no.7, pp.4486-4497, July 2022. 10.1109\/TCSVT.2021.3127149","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"36","doi-asserted-by":"publisher","unstructured":"[36] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, \u201cSLIC superpixels compared to state-of-the-art superpixel methods,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.34, no.11, pp.2274-2282, Nov. 2012. 10.1109\/TPAMI.2012.120","DOI":"10.1109\/TPAMI.2012.120"},{"key":"37","doi-asserted-by":"publisher","unstructured":"[37] X. Zhang, Y. Wang, Z. Chen, J. Yan and D. Wang, \u201cSaliency detection via image sparse representation and color features combination,\u201d Multimed. Tools Appl., June 2020. 10.1007\/s11042-020-09073-4","DOI":"10.1007\/s11042-020-09073-4"},{"key":"38","doi-asserted-by":"publisher","unstructured":"[38] D. Cheng, R. Liu, J. Li, S. Liang, Q. Kou, and K. Zhao, \u201cActivity guided multi-scales collaboration based on scaled-CNN for saliency prediction,\u201d Image Vision Comput., vol.114, Oct. 2021. 10.1016\/j.imavis.2021.104267","DOI":"10.1016\/j.imavis.2021.104267"},{"key":"39","doi-asserted-by":"publisher","unstructured":"[39] Z. Che, A. Borji, G. Zhai, X. Min, G. Guo, and P. Le Callet, \u201cHow is Gaze influenced by image transformations? Dataset and model,\u201d IEEE Trans. Image Process. vol.29, pp.29-2287, 2020. 10.1109\/TIP.2019.2945857","DOI":"10.1109\/TIP.2019.2945857"},{"key":"40","doi-asserted-by":"publisher","unstructured":"[40] G. Ding, N. Mamolu, A. Caglayan, M. Murakawa, and R. Nakamura, \u201cSalFBNet: Learning pseudo-saliency distribution via feedback convolutional networks,\u201d Image Vision Comput., vol.120, April 2022. 10.1016\/j.imavis.2022.104395","DOI":"10.1016\/j.imavis.2022.104395"},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] T. Judd, K. Ehinger, F. Durand, and A. Torralba, \u201cLearning to predict where humans look,\u201d IEEE International Conference on Computer Vision, 2010. 10.1109\/ICCV.2009.5459462","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"42","unstructured":"[42] T. Judd, F. Durand, and A. Torralba, \u201cA benchmark of computational models of saliency to predict human fixations,\u201d MIT Computer Science and Artificial Intelligence Laboratory Technical Report, 2012."},{"key":"43","unstructured":"[43] A. Borji and L. Itti, \u201cCAT2000: A large scale fixation dataset for boosting saliency research,\u201d Computer Vision and Pattern Recognition, arXiv, 2015. 10.48550\/arXiv.1505.03581"},{"key":"44","unstructured":"[44] H. Xun, C. Shen, X. Boix, and Q. Zhao, \u201cSALICON: Reducing the semantic gap in saliency prediction by adapting deep neural networks,\u201d 2015 IEEE International Conference on Computer Vision (ICCV), 2015. 10.1109\/ICCV.2015.38"},{"key":"45","doi-asserted-by":"publisher","unstructured":"[45] L.Q. Chen, X. Xie, X. Fan, W.-Y. Ma, H.-J. Zhang and H.-Q. Zhou, \u201cA visual attention model for adapting images on small displays,\u201d Multimedia Systems, Oct. 2003. 10.1007\/s00530-003-0105-4","DOI":"10.1007\/s00530-003-0105-4"},{"key":"46","doi-asserted-by":"publisher","unstructured":"[46] Z. Bylinskii, T. Judd, A. Oliva, A. Torralba, and F. Durand, \u201cWhat do different evaluation metrics tell us about saliency models?,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.41, no.3, pp.740-757, March 2017. 10.1109\/TPAMI.2018.2815601","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"47","doi-asserted-by":"crossref","unstructured":"[47] A. Borji, H.R. Tavakoli, D.N. Sihite, and L. Itti, \u201cAnalysis of scores, datasets, and models in visual saliency prediction,\u201d IEEE International Conference on Computer Vision, 2014. 10.1109\/ICCV.2013.118","DOI":"10.1109\/ICCV.2013.118"},{"key":"48","doi-asserted-by":"crossref","unstructured":"[48] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg and L. Fei-Fei, \u201cImageNet large scale visual recognition challenge,\u201d Int. J. Comput. Vis., April 2015. 10.1007\/s11263-015-0816-y","DOI":"10.1007\/s11263-015-0816-y"},{"key":"49","unstructured":"[49] D. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d Comput. Sci., 2014. 10.48550\/arXiv.1412.6980"},{"key":"50","doi-asserted-by":"publisher","unstructured":"[50] P. Li, X. Xing, X. Xu, B. Cai, and J. Cheng, \u201cAttention-aware concentrated network for saliency prediction,\u201d Neurocomputing, vol.429, pp.199-214, March 2021. 10.1016\/j.neucom.2020.10.083","DOI":"10.1016\/j.neucom.2020.10.083"},{"key":"51","doi-asserted-by":"crossref","unstructured":"[51] S. Fan, Z. Shen, J. Ming, B.L. Koenig, J. Xu, M.S. Kankanhalli, and Q. Zhao, \u201cEmotional attention: A study of image sentiment and visual attention,\u201d 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 10.1109\/CVPR.2018.00785","DOI":"10.1109\/CVPR.2018.00785"},{"key":"52","doi-asserted-by":"crossref","unstructured":"[52] A. Linardos, M. K\u00fcmmerer, and O. Press, M. Bethge, \u201cDeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling,\u201d 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 10.1109\/ICCV48922.2021.01268","DOI":"10.1109\/ICCV48922.2021.01268"},{"key":"53","doi-asserted-by":"crossref","unstructured":"[53] C. Fosco, A. Newman, P. Sukhum, Y. Bin Zhang, N. Zhao, A. Oliva, and Z. Bylinskii, \u201cHow much time do you have? modeling multi-duration saliency,\u201d Computer Vision and Pattern Recognition, 2020. 10.1109\/CVPR42600.2020.00453","DOI":"10.1109\/CVPR42600.2020.00453"},{"key":"54","doi-asserted-by":"publisher","unstructured":"[54] S. Yang, G. Lin, Q. Jiang, and W. Lin, \u201cA dilated inception network for visual saliency prediction,\u201d IEEE Trans. Multimedia, vol.22, no.8, pp.2163-2176, Aug. 2019. 10.1109\/TMM.2019.2947352","DOI":"10.1109\/TMM.2019.2947352"},{"key":"55","doi-asserted-by":"crossref","unstructured":"[55] R. Droste, J. Jiao, and J.A. Noble, \u201cUnified image and video saliency modeling,\u201d ECCV 2020, pp.419-435, Oct. 2020. 10.1007\/978-3-030-58558-7_25","DOI":"10.1007\/978-3-030-58558-7_25"},{"key":"56","doi-asserted-by":"publisher","unstructured":"[56] A. Kroner, M. Senden, K. Driessens, and R. Goebel, \u201cContextual encoder-decoder network for visual saliency prediction,\u201d Neural Netw.vol.129, pp.261-270, Sept. 2019. 10.1016\/j.neunet.2020.05.004","DOI":"10.1016\/j.neunet.2020.05.004"},{"key":"57","doi-asserted-by":"crossref","unstructured":"[57] G. Ding, N. Imamoglu, A. Caglayan, M. Murakawa, and R. Nakamura, \u201cFBNet: FeedBack-recursive CNN for saliency detection,\u201d 17th International Conference on Machine Vision Applications (MVA), 2021. 10.23919\/MVA51890.2021.9511371","DOI":"10.23919\/MVA51890.2021.9511371"},{"key":"58","doi-asserted-by":"publisher","unstructured":"[58] S. Fang, J. Li, Y. Tian, T. Huang, and X. Chen, \u201cLearning discriminative subspaces on random contrasts for image saliency analysis,\u201d IEEE Trans. Neural Netw. Learn. Syst., vol.28, no.5, pp.1095-1108, May 2017. 10.1109\/TNNLS.2016.2522440","DOI":"10.1109\/TNNLS.2016.2522440"},{"key":"59","doi-asserted-by":"crossref","unstructured":"[59] J. Zhang and S. Sclaroff, \u201cSaliency detection: A boolean map approach,\u201d 2013 IEEE International Conference on Computer Vision, 2013. 10.1109\/ICCV.2013.26","DOI":"10.1109\/ICCV.2013.26"},{"key":"60","doi-asserted-by":"publisher","unstructured":"[60] E. Erdem and A. Erdem, \u201cVisual saliency estimation by nonlinearly integrating features using region covariances,\u201d J. Vis., vol.13, no.11, March 2013. 10.1167\/13.4.11","DOI":"10.1167\/13.4.11"},{"key":"61","doi-asserted-by":"publisher","unstructured":"[61] W. Wang and J. Shen, \u201cDeep Visual attention prediction,\u201d IEEE Trans. Image Process., vol.27, no.5, pp.2368-2378, May 2018. 10.1109\/TIP.2017.2787612","DOI":"10.1109\/TIP.2017.2787612"},{"key":"62","doi-asserted-by":"crossref","unstructured":"[62] M. Cornia, L. Baraldi, G. Serra, and R. Cucchiara, \u201cA Deep multi-level network for saliency prediction,\u201d International Conference on Pattern Recognition, 2016. 10.1109\/ICPR.2016.7900174","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"63","doi-asserted-by":"crossref","unstructured":"[63] M. Jiang and Q. Zhao, \u201cLearning visual attention to identify people with autism spectrum disorder,\u201d 16th IEEE International Conference on Computer Vision (ICCV), 2017. 10.1109\/ICCV.2017.354","DOI":"10.1109\/ICCV.2017.354"},{"key":"64","doi-asserted-by":"publisher","unstructured":"[64] Y. Xu, S. Gao, J. Wu, N. Li, and J. Yu, \u201cPersonalized saliency and its prediction,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.41, no.12, pp.2975-2989, Dec. 2019. 10.1109\/TPAMI.2018.2866563","DOI":"10.1109\/TPAMI.2018.2866563"},{"key":"65","doi-asserted-by":"publisher","unstructured":"[65] L. Zhang, M.H. Tong, T.K. Marks, H. Shan, and G.W. Cottrell, \u201cSUN: A Bayesian framework for saliency using natural statistics,\u201d J. Vis., vol.8, no.7, Dec. 2008. 10.1167\/8.7.32","DOI":"10.1167\/8.7.32"},{"key":"66","unstructured":"[66] D. Zanca and M. Gori, \u201cVariational laws of visual attention for dynamic scenes,\u201d Proc. NIPS, pp.3826-3835, Dec. 2017."},{"key":"67","doi-asserted-by":"publisher","unstructured":"[67] N. Rabbani, B. Nazari, S. Sadri, and R. Rikhtehgaran, \u201cEfficient Bayesian approach to saliency detection based on Dirichlet process mixture,\u201d IET Image Proc., vol.11, no.11, pp.1103-1113, Nov. 2017. 10.1049\/iet-ipr.2017.0267","DOI":"10.1049\/iet-ipr.2017.0267"},{"key":"68","doi-asserted-by":"crossref","unstructured":"[68] S. Woo, J. Park, J.-Y. Lee, and I.S. Kweon, \u201cCBAM: Convolutional block attention module,\u201d the 15th European Conference on Computer Vision (ECCV), pp.3-19, Oct. 2018. 10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/9\/E106.D_2022EDP7220\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T04:31:09Z","timestamp":1693629069000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/9\/E106.D_2022EDP7220\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":68,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022edp7220","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]},"article-number":"2022EDP7220"}}