{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T16:10:01Z","timestamp":1747930201850,"version":"3.41.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319168104"},{"type":"electronic","value":"9783319168111"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-16811-1_14","type":"book-chapter","created":{"date-parts":[[2015,4,15]],"date-time":"2015-04-15T09:48:40Z","timestamp":1429091320000},"page":"205-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Modeling the Temporality of Saliency"],"prefix":"10.1007","author":[{"given":"Ye","family":"Luo","sequence":"first","affiliation":[]},{"given":"Loong-Fah","family":"Cheong","sequence":"additional","affiliation":[]},{"given":"John-John","family":"Cabibihan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,4,16]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: NIPS, pp. 545\u2013552 (2007)","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"14_CR2","first-page":"1","volume":"8","author":"W Einhauser","year":"2008","unstructured":"Einhauser, W., Spain, M., Perona, P.: Objects predict fixations better than early saliency. J. Vis. 8, 1\u201326 (2008)","journal-title":"J. Vis."},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: ICCV, pp. 2106\u20132113 (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"14_CR4","unstructured":"Cerf, M., Harel, J., Einhaeuser, W., Koch, C.: Predicting human gaze using low-level saliency combined with face detection. In: NIPS, pp. 241\u2013248 (2008)"},{"key":"14_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-010-0375-1","volume":"11","author":"Q Zhao","year":"2011","unstructured":"Zhao, Q., Koch, C.: Learning a saliency map using fixated locations in natural scenes. J. Vis. 11, 1\u201315 (2011)","journal-title":"J. Vis."},{"key":"14_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/9.12.10","volume":"9","author":"M Cerf","year":"2009","unstructured":"Cerf, M., Koch, C.: Faces and text attract gaze independent of the task: experimental data and computer model. J. Vis. 9, 1\u201315 (2009)","journal-title":"J. Vis."},{"key":"14_CR7","unstructured":"Shen, C., Mingli, S., Zhao, Q.: Learning high-level concepts by training a deep network on eye fixations. In: Deep Learning and Unsupervised Feature Learning Workshop, in Conjunction with NIPS (2012)"},{"key":"14_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/7.8.2","volume":"7","author":"CC Fowlkes","year":"2007","unstructured":"Fowlkes, C.C., Martin, D.R., Malik, J.: Local figure-ground cues are valid for natural images. J. Vis. 7, 1\u20139 (2007)","journal-title":"J. Vis."},{"key":"14_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-014-0730-8","volume":"14","author":"J Xu","year":"2014","unstructured":"Xu, J., Jiang, M., Wang, S., Kankanhalli, M.S., Zhao, Q.: Predicting human gaze beyond pixels. J. Vis. 14, 1\u201320 (2014)","journal-title":"J. Vis."},{"key":"14_CR10","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1177\/1534582305276839","volume":"4","author":"R Blake","year":"2005","unstructured":"Blake, R., Lee, S.H.: The role of temporal structure in human vision. Behav. Cogn. Neurosci. Rev. 4, 21\u201342 (2005)","journal-title":"Behav. Cogn. Neurosci. Rev."},{"key":"14_CR11","first-page":"669","volume":"37","author":"T Gao","year":"2011","unstructured":"Gao, T., Scholl, B.: Chasing vs. stalking: Interrupting the perception of animacy. J. Exp. Psychol. 37, 669\u2013684 (2011)","journal-title":"J. Exp. Psychol."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Ballas, N., Yang, Y., Lan, Z.Z., Delezoide, B., Preteux, F., Hauptmann, A.: Space-time robust representation for action recognition. In: ICCV, pp. 2704\u20132711 (2013)","DOI":"10.1109\/ICCV.2013.336"},{"key":"14_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/9.12.15","volume":"9","author":"HJJ Seo","year":"2009","unstructured":"Seo, H.J.J., Milanfar, P.: Static and space-time visual saliency detection by self-resemblance. J. Vis. 9, 1\u201327 (2009)","journal-title":"J. Vis."},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, Y., Huang, Q., Gao, W.: Measuring visual saliency by site entropy rate. In: CVPR, pp. 2368\u20132375 (2010)","DOI":"10.1109\/CVPR.2010.5539927"},{"key":"14_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1007\/978-3-642-37431-9_45","volume-title":"Computer Vision \u2013 ACCV 2012","author":"N Riche","year":"2013","unstructured":"Riche, N., Mancas, M., Culibrk, D., Crnojevic, V., Gosselin, B., Dutoit, T.: Dynamic saliency models and human attention: a comparative study on videos. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part III. LNCS, vol. 7726, pp. 586\u2013598. Springer, Heidelberg (2013)"},{"key":"14_CR16","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TPAMI.2012.89","volume":"35","author":"A Borji","year":"2013","unstructured":"Borji, A., Itti, L.: State-of-the-art in visual attention modeling. T-PAMI 35, 185\u2013207 (2013)","journal-title":"T-PAMI"},{"key":"14_CR17","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1109\/TPAMI.2009.112","volume":"32","author":"V Mahadevan","year":"2010","unstructured":"Mahadevan, V., Vasconcelos, N.: Spatiotemporal saliency in dynamic scenes. T-PAMI 32, 171\u2013177 (2010)","journal-title":"T-PAMI"},{"key":"14_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1007\/978-3-642-15555-0_27","volume-title":"Computer Vision \u2013 ECCV 2010","author":"E Rahtu","year":"2010","unstructured":"Rahtu, E., Kannala, J., Salo, M., Heikkil\u00e4, J.: Segmenting salient objects from images and videos. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 366\u2013379. Springer, Heidelberg (2010)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, F., Kang, S.B., Cohen, M.F.: Time-mapping using space-time saliency. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.429"},{"key":"14_CR20","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. T-PAMI 20, 1254\u20131259 (1998)","journal-title":"T-PAMI"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhou, Y., Xu, L., Yang, X., Yang, J.: Incremental sparse saliency detection. In: ICIP, pp. 3093\u20133096 (2009)","DOI":"10.1109\/ICIP.2009.5414465"},{"key":"14_CR22","unstructured":"Zhang, L., Tong, M.H., Cottrell, G.W.: SUNDAy: saliency using natural statistics for dynamic analysis of scenes. In: The Thirty-First Annual Cognitive Science Society Conference, pp. 1\u20136 (2009)"},{"key":"14_CR23","unstructured":"Hou, X., Zhang, L.: Dynamic visual attention: searching for coding length increments. In: NIPS, pp. 681\u2013688 (2008)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Itti, L., Baldi, P.: A principled approach to detecting surprising events in video. In: CVPR, pp. 631\u2013637 (2005)","DOI":"10.1109\/CVPR.2005.40"},{"key":"14_CR25","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TPAMI.2012.28","volume":"34","author":"B Alexe","year":"2012","unstructured":"Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. T-PAMI 34, 2189\u20132202 (2012)","journal-title":"T-PAMI"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Bergh, M.V.D., Roig, G., Boix, X., Manen, S., Gool, L.V.: Online video seeds for temporal window objectness. In: ICCV, pp. 377\u2013384 (2013)","DOI":"10.1109\/ICCV.2013.54"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-642-15555-0_21","volume-title":"Computer Vision \u2013 ECCV 2010","author":"T Brox","year":"2010","unstructured":"Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 282\u2013295. Springer, Heidelberg (2010)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Ochs, P., Brox, T.: Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions. In: ICCV, pp. 1583\u20131590 (2011)","DOI":"10.1109\/ICCV.2011.6126418"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: CVPR, pp. 628\u2013635 (2013)","DOI":"10.1109\/CVPR.2013.87"},{"key":"14_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/11.5.5","volume":"11","author":"BW Tatler","year":"2011","unstructured":"Tatler, B.W., Hayhoe, M.M., Land, M.F., Ballard, D.H.: Eye guidance in natural vision: Reinterpreting salience. J. Vis. 11, 1\u201323 (2011)","journal-title":"J. Vis."},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Chang, J., Wei, D., III, J.W.F.: A video representation using temporal superpixels. In: CVPR, pp. 2051\u20132058 (2013)","DOI":"10.1109\/CVPR.2013.267"},{"key":"14_CR32","unstructured":"Borga, M.: Learning Multidimensional Signal Processing. Ph.D. thesis, Link\u00f6ping University, Sweden, SE-581 83 Link\u00f6ping, Sweden (1998)"},{"key":"14_CR33","unstructured":"Shapovalova, N., Raptis, M., Sigal, L., Mori, G.: Action is in the eye of the beholder: eye-gaze driven model for spatio-temporal action localization. In: NIPS, pp. 2409\u20132417 (2013)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Fukuchi, K., Miyazato, K., Kimura, A., Takagi, S., Yamato, J.: Saliency-based video segmentation with graph cuts and sequentially updated priors. In: Proceeding of International Conference on Multimedia and Expo (ICME), pp. 638\u2013641 (2009)","DOI":"10.1109\/ICME.2009.5202577"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Riche, N., Duvinage, M., Mancas, M., Gosselin, B., Dutoit, T.: Saliency and human fixations: state-of-the-art and study of comparison metrics. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.147"},{"key":"14_CR36","first-page":"55","volume":"1","author":"A Borji","year":"2012","unstructured":"Borji, A., Sihite, D.N., Itti, L.: Quantitative analysis of human-model agreement in visual saliency modeling: a comparative study. TIP 1, 55\u201369 (2012)","journal-title":"TIP"},{"key":"14_CR37","doi-asserted-by":"publisher","first-page":"2397","DOI":"10.1016\/j.visres.2005.03.019","volume":"45","author":"RJ Peters","year":"2005","unstructured":"Peters, R.J., Iyer, A., Itti, L., Koch, C.: Components of bottom-up gaze allocation in natural images. Vision. Res. 45, 2397\u20132416 (2005)","journal-title":"Vision. Res."},{"key":"14_CR38","first-page":"107","volume":"100","author":"T Jost","year":"2005","unstructured":"Jost, T., Ouerhani, N., von Wartburg, R., Muri, R., Hugli, H.: Assessing the contribution of color in visual attention. CVIU 100, 107\u2013123 (2005)","journal-title":"CVIU"},{"key":"14_CR39","volume-title":"Signal Detection Theory and Psychophysics","author":"DM Green","year":"1966","unstructured":"Green, D.M., Swets, J.A.: Signal Detection Theory and Psychophysics. Wiley, New York (1966)"},{"key":"14_CR40","first-page":"1856","volume":"57","author":"C Guo","year":"2010","unstructured":"Guo, C., Zhang, L.: A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. TIP 57, 1856\u20131866 (2010)","journal-title":"TIP"}],"container-title":["Lecture Notes in Computer Science","Computer Vision -- ACCV 2014"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-16811-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T15:28:01Z","timestamp":1747927681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-16811-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319168104","9783319168111"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-16811-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"16 April 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}