{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:49:39Z","timestamp":1740098979828,"version":"3.37.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319701684"},{"type":"electronic","value":"9783319701691"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-70169-1_29","type":"book-chapter","created":{"date-parts":[[2017,11,6]],"date-time":"2017-11-06T02:14:23Z","timestamp":1509934463000},"page":"387-399","source":"Crossref","is-referenced-by-count":1,"title":["Attentive Models in Vision: Computing Saliency Maps in the Deep Learning Era"],"prefix":"10.1007","author":[{"given":"Marcella","family":"Cornia","sequence":"first","affiliation":[]},{"given":"Davide","family":"Abati","sequence":"additional","affiliation":[]},{"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Palazzi","sequence":"additional","affiliation":[]},{"given":"Simone","family":"Calderara","sequence":"additional","affiliation":[]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,11,7]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Alletto, S., Palazzi, A., Solera, F., Calderara, S., Cucchiara, R.: DR(eye)VE: a dataset for attention-based tasks with applications to autonomous and assisted driving. In: CVPR Workshops (2016)","DOI":"10.1109\/CVPRW.2016.14"},{"key":"29_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: Hierarchical boundary-aware neural encoder for video captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.339"},{"key":"29_CR4","unstructured":"Bazzani, L., Larochelle, H., Torresani, L.: Recurrent mixture density network for spatiotemporal visual attention. In: ICLR (2017)"},{"key":"29_CR5","unstructured":"Bruce, N., Tsotsos, J.: Saliency based on information maximization. In: ANIPS, pp. 155\u2013162 (2005)"},{"key":"29_CR6","unstructured":"Bylinskii, Z., Judd, T., Borji, A., Itti, L., Durand, F., Oliva, A., Torralba, A.: Mit saliency benchmark. http:\/\/saliency.mit.edu\/"},{"key":"29_CR7","unstructured":"Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., Durand, F.: What do different evaluation metrics tell us about saliency models? arXiv preprint arXiv:1604.03605 (2016)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: A deep multi-level network for saliency prediction. In: ICPR (2016)","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"29_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/978-3-319-48881-3_21","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"M Cornia","year":"2016","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: Multi-level net: a visual saliency prediction model. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 302\u2013315. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_21"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: Predicting human eye fixations via an LSTM-based saliency attentive model. arXiv preprint arXiv:1611.09571 (2017)","DOI":"10.1109\/TIP.2018.2851672"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: Visual saliency for image captioning in new multimedia services. In: ICME Workshops (2017)","DOI":"10.1109\/ICMEW.2017.8026277"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Greenspan, H., Belongie, S., Goodman, R., Perona, P., Rakshit, S., Anderson, C.H.: Overcomplete steerable pyramid filters and rotation invariance. In: CVPR (1994)","DOI":"10.1109\/CVPR.1994.323833"},{"issue":"1","key":"29_CR13","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TIP.2013.2282897","volume":"23","author":"H Hadizadeh","year":"2014","unstructured":"Hadizadeh, H., Baji, I.V.: Saliency-aware video compression. IEEE Trans. Image Process. 23(1), 19\u201333 (2014)","journal-title":"IEEE Trans. Image Process."},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: ANIPS, pp. 545\u2013552 (2006)","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., Zhao, Q.: SALICON: reducing the semantic gap in saliency prediction by adapting deep neural networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.38"},{"issue":"3","key":"29_CR17","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/35058500","volume":"2","author":"L Itti","year":"2001","unstructured":"Itti, L., Koch, C.: Computational modelling of visual attention. Nat. Rev. Neurosci. 2(3), 194\u2013203 (2001)","journal-title":"Nat. Rev. Neurosci."},{"issue":"11","key":"29_CR18","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E., et al.: A model of saliency-based visual attention for rapid scene analysis. IEEE TPAMI 20(11), 1254\u20131259 (1998)","journal-title":"IEEE TPAMI"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Jetley, S., Murray, N., Vig, E.: End-to-end saliency mapping via probability distribution prediction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.620"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, M., Huang, S., Duan, J., Zhao, Q.: Salicon: saliency in context. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"29_CR21","unstructured":"Judd, T., Durand, F., Torralba, A.: A benchmark of computational models of saliency to predict human fixations. MIT Technical report (2012)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"29_CR23","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-94-009-3833-5_5","volume-title":"Matters of Intelligence","author":"C Koch","year":"1987","unstructured":"Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. In: Vaina, L.M. (ed.) Matters of Intelligence, pp. 115\u2013141. Springer, Dordrecht (1987). https:\/\/doi.org\/10.1007\/978-94-009-3833-5_5"},{"key":"29_CR24","unstructured":"Kruthiventi, S.S., Ayush, K., Babu, R.V.: Deepfix: a fully convolutional neural network for predicting human eye fixations. arXiv preprint arXiv:1510.02927 (2015)"},{"key":"29_CR25","unstructured":"K\u00fcmmerer, M., Theis, L., Bethge, M.: DeepGaze I: Boosting saliency prediction with feature maps trained on ImageNet. In: ICLR Workshops (2015)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Palazzi, A., Solera, F., Calderara, S., Alletto, S., Cucchiara, R.: Learning to attend like a human driver. In: Intelligent Vehicles Symposium (2017)","DOI":"10.1109\/IVS.2017.7995833"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Pan, J., Sayrol, E., Giro-i-Nieto, X., McGuinness, K., Gir\u00f3-i, N.X.: Shallow and deep convolutional networks for saliency prediction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.71"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Rudoy, D., Goldman, D.B., Shechtman, E., Zelnik-Manor, L.: Learning video saliency from human gaze using candidate selection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.152"},{"key":"29_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"issue":"7","key":"29_CR30","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/TPAMI.2014.2366154","volume":"37","author":"S Mathe","year":"2015","unstructured":"Mathe, S., Sminchisescu, C.: Actions in the eye: dynamic gaze datasets and learnt saliency models for visual recognition. IEEE TPAMI 37(7), 1408\u20131424 (2015)","journal-title":"IEEE TPAMI"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"1","key":"29_CR32","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"AM Treisman","year":"1980","unstructured":"Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97\u2013136 (1980)","journal-title":"Cogn. Psychol."},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Vig, E., Dorr, M., Cox, D.: Large-scale optimization of hierarchical features for saliency prediction in natural images. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.358"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J., Porikli, F.: Saliency-aware geodesic video object segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298961"},{"issue":"11","key":"29_CR35","doi-asserted-by":"crossref","first-page":"4185","DOI":"10.1109\/TIP.2015.2460013","volume":"24","author":"W Wang","year":"2015","unstructured":"Wang, W., Shen, J., Shao, L.: Consistent video saliency using local gradient flow optimization and global refinement. IEEE Trans. Image Process. 24(11), 4185\u20134196 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"29_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Shah, M.: Visual attention detection in video sequences using spatiotemporal cues. In: ACM MM (2006)","DOI":"10.1145\/1180639.1180824"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, J., Sclaroff, S.: Saliency detection: a boolean map approach. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.26"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Zhong, S.H., Liu, Y., Ren, F., Zhang, J., Ren, T.: Video saliency detection via dynamic consistent spatio-temporal attention modelling. In: AAAI (2013)","DOI":"10.1609\/aaai.v27i1.8642"}],"container-title":["Lecture Notes in Computer Science","AI*IA 2017 Advances in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70169-1_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:45:14Z","timestamp":1693183514000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-70169-1_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319701684","9783319701691"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70169-1_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}