{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T23:58:39Z","timestamp":1774137519655,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642337086","type":"print"},{"value":"9783642337093","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33709-3_60","type":"book-chapter","created":{"date-parts":[[2012,9,26]],"date-time":"2012-09-26T08:05:20Z","timestamp":1348646720000},"page":"842-856","source":"Crossref","is-referenced-by-count":63,"title":["Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition"],"prefix":"10.1007","author":[{"given":"Stefan","family":"Mathe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cristian","family":"Sminchisescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"60_CR1","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)","DOI":"10.1109\/CVPRW.2009.5206557"},{"key":"60_CR2","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.D., Ahmed, J., Shah, M.: Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"60_CR3","doi-asserted-by":"crossref","unstructured":"Everingham, M., Gool, L.V., Williams, C., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. IJCV (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"60_CR4","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":"60_CR5","unstructured":"Larochelle, H., Hinton, G.: Learning to combine foveal glimpses with a third-order boltzmann machine. In: NIPS (2010)"},{"key":"60_CR6","doi-asserted-by":"crossref","unstructured":"Laptev, I.: On space-time interest points. In: IJCV (2005)","DOI":"10.1007\/s11263-005-1838-7"},{"key":"60_CR7","unstructured":"Han, D., Bo, L., Sminchisescu, C.: Selection and context for action recognition. In: ICCV (2009)"},{"key":"60_CR8","doi-asserted-by":"crossref","unstructured":"Prest, A., Schmid, C., Ferrari, V.: Weakly supervised learning of interactions between humans and objects. PAMI (2011)","DOI":"10.1109\/TPAMI.2011.158"},{"key":"60_CR9","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"60_CR10","doi-asserted-by":"crossref","unstructured":"Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research\u00a040 (2000)","DOI":"10.1016\/S0042-6989(99)00163-7"},{"key":"60_CR11","doi-asserted-by":"crossref","unstructured":"Ehinger, K.A., Sotelo, B., Torralba, A., Oliva, A.: Modeling search for people in 900 scenes: A combined source model of eye guidance. Visual Cognition\u00a017 (2009)","DOI":"10.1080\/13506280902834720"},{"key":"60_CR12","doi-asserted-by":"crossref","unstructured":"Judd, T., Durand, F., Torralba, A.: Fixations on low resolution images. In: ICCV (2009)","DOI":"10.1167\/10.7.142"},{"key":"60_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-540-74936-3_41","volume-title":"Pattern Recognition","author":"W. Kienzle","year":"2007","unstructured":"Kienzle, W., Sch\u00f6lkopf, B., Wichmann, F.A., Franz, M.O.: How to Find Interesting Locations in Video: A Spatiotemporal Interest Point Detector Learned from Human Eye Movements. In: Hamprecht, F.A., Schn\u00f6rr, C., J\u00e4hne, B. (eds.) DAGM 2007. LNCS, vol.\u00a04713, pp. 405\u2013414. Springer, Heidelberg (2007)"},{"key":"60_CR14","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Iyer, A., Koch, C., Perona, P.: What do we perceive in a glance of a real-world scene? Journal of Vision (2007)","DOI":"10.1167\/7.1.10"},{"key":"60_CR15","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Serre, T., Wolf, L., Poggio, T.: A biologically inspired system for action recognition. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408988"},{"key":"60_CR16","unstructured":"Itti, L., Rees, G., Tsotsos, J.K. (eds.): Neurobiology of Attention. Academic Press (2005)"},{"key":"60_CR17","series-title":"LNCS","first-page":"84","volume-title":"ECCV 2012, Part VII","author":"E. Vig","year":"2012","unstructured":"Vig, E., Dorr, M., Cox, D.: Space-Variant Descriptor Sampling for Action Recognition Based on Saliency and Eye Movements. In: Fitzgibbon, A., Lazebnik, S., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol.\u00a07578, pp. 84\u201397. Springer, Heidelberg (2012)"},{"key":"60_CR18","unstructured":"Land, M.F., Tatler, B.W.: Looking and Acting. Oxford University Press (2009)"},{"key":"60_CR19","doi-asserted-by":"crossref","unstructured":"Torralba, A., Oliva, A., Castelhano, M., Henderson, J.: Contextual guidance of eye movements and attention in real-world scenes: The role of global features in object search. Psychological Review\u00a013 (2006)","DOI":"10.1037\/0033-295X.113.4.766"},{"key":"60_CR20","doi-asserted-by":"crossref","unstructured":"Borji, A., Itti, L.: Scene classification with a sparse set of salient regions. In: ICRA (2011)","DOI":"10.1109\/ICRA.2011.5979815"},{"key":"60_CR21","doi-asserted-by":"crossref","unstructured":"Elazary, L., Itti, L.: A Bayesian model for efficient visual search and recognition. Vision Research\u00a050 (2010)","DOI":"10.1016\/j.visres.2010.01.002"},{"key":"60_CR22","doi-asserted-by":"crossref","unstructured":"Wang, H., Klaser, A., Schmid, C.: Liu, C.: Action recognition by dense trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"60_CR23","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Z., Liu, Z.: Expandable data-driven graphical modeling of human actions based on salient postures. In: IEEE TCSVT, vol.\u00a018 (2008)","DOI":"10.1109\/TCSVT.2008.2005597"},{"key":"60_CR24","unstructured":"Mathe, S., Sminchisescu, C.: Actions in the eye: dynamic gaze datasets and learnt saliency models for visual recognition. Technical report, Institute of Mathematics of the Romanian Academy and University of Bonn (February 2012)"},{"key":"60_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-5379-7","volume-title":"Eye Movements and Vision","author":"A. Yarbus","year":"1967","unstructured":"Yarbus, A.: Eye Movements and Vision. Plenum Press, New York (1967)"},{"key":"60_CR26","doi-asserted-by":"crossref","unstructured":"Hwang, A., Wang, H., Pomplun, M.: Semantic guidance of eye movements in real-world scenes. Vision Research (2011)","DOI":"10.1016\/j.visres.2011.03.010"},{"key":"60_CR27","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV (42) (2001)"},{"key":"60_CR28","doi-asserted-by":"crossref","unstructured":"Rosenholtz, R.: A simple saliency model predicts a number of motion popout phenomena. Vision Research (39) (1999)","DOI":"10.1016\/S0042-6989(99)00077-2"},{"key":"60_CR29","unstructured":"Viola, P., Jones, M.: Robust real-time object detection. IJCV (2001)"},{"key":"60_CR30","doi-asserted-by":"crossref","unstructured":"Felzenswalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"60_CR31","unstructured":"Li, F., Guy, L., Sminchisescu, C.: Chebyshev approximations to the histogram chi-square kernel. In: CVPR (2012)"},{"key":"60_CR32","unstructured":"Simocelli, E., Freeman, W.: The steerable pyramid: A flexible architecture for multi-scale derivative computation. In: ICIP (1995)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2012"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33709-3_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T16:27:35Z","timestamp":1643473655000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33709-3_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642337086","9783642337093"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33709-3_60","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}