{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:06:21Z","timestamp":1775678781051,"version":"3.50.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464534","type":"print"},{"value":"9783319464541","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46454-1_28","type":"book-chapter","created":{"date-parts":[[2016,9,15]],"date-time":"2016-09-15T09:15:09Z","timestamp":1473930909000},"page":"454-471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Detecting Engagement in Egocentric Video"],"prefix":"10.1007","author":[{"given":"Yu-Chuan","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,16]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Rudoy, D., Goldman, D., Shechtman, E., Zelnik-Manor, L.: Learning video saliency from human gaze using candidate selection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.152"},{"key":"28_CR2","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.neucom.2014.05.049","volume":"145","author":"J Han","year":"2014","unstructured":"Han, J., Sun, L., Hu, X., Han, J., Shao, L.: Spatial and temporal visual attention prediction in videos using eye movement data. Neurocomputing 145, 140\u2013153 (2014)","journal-title":"Neurocomputing"},{"issue":"11","key":"28_CR3","first-page":"3028","volume":"20","author":"W Lee","year":"2011","unstructured":"Lee, W., Huang, T., Yeh, S., Chen, H.: Learning-based prediction of visual attention for video signals. IEEE TIP 20(11), 3028\u20133038 (2011)","journal-title":"IEEE TIP"},{"issue":"1","key":"28_CR4","first-page":"28","volume":"12","author":"G Abdollahian","year":"2010","unstructured":"Abdollahian, G., Taskiran, C., Pizlo, Z., Delp, E.: Camera motion-based analysis of user generated video. TMM 12(1), 28\u201341 (2010)","journal-title":"TMM"},{"issue":"1","key":"28_CR5","first-page":"171","volume":"32","author":"V Mahadevan","year":"2010","unstructured":"Mahadevan, V., Vasconcelos, N.: Spatiotemporal saliency in dynamic scenes. TPAMI 32(1), 171\u2013177 (2010)","journal-title":"Spatiotemporal saliency in dynamic scenes. TPAMI"},{"key":"28_CR6","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. LNCS, vol. 6315, pp. 366\u2013379. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15555-0_27"},{"issue":"10","key":"28_CR7","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1016\/j.visres.2008.09.007","volume":"49","author":"L Itti","year":"2009","unstructured":"Itti, L., Baldi, P.: Bayesian surprise attracts human attention. Vision Res. 49(10), 1295\u20131306 (2009)","journal-title":"Vision Res."},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Liu, H., Jiang, S., Huang, Q., Xu, C.: A generic virtual content insertion system based on visual attention analysis. In: ACM MM (2008)","DOI":"10.1145\/1459359.1459410"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., Fathi, A., Rehg, J.M.: Learning to predict gaze in egocentric video. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.399"},{"key":"28_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-3-642-25367-6_25","volume-title":"Advances in Image and Video Technology","author":"K Yamada","year":"2011","unstructured":"Yamada, K., Sugano, Y., Okabe, T., Sato, Y., Sugimoto, A., Hiraki, K.: Attention prediction in egocentric video using motion and visual saliency. In: Ho, Y.-S. (ed.) PSIVT 2011. LNCS, vol. 7087, pp. 277\u2013288. Springer, Heidelberg (2011). doi: 10.1007\/978-3-642-25367-6_25"},{"key":"28_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-642-22822-3_42","volume-title":"Computer Vision \u2013 ACCV 2010 Workshops","author":"K Yamada","year":"2011","unstructured":"Yamada, K., Sugano, Y., Okabe, T., Sato, Y., Sugimoto, A., Hiraki, K.: Can saliency map models predict human egocentric visual attention? In: Koch, R., Huang, F. (eds.) ACCV 2010. LNCS, vol. 6468, pp. 420\u2013429. Springer, Heidelberg (2011). doi: 10.1007\/978-3-642-22822-3_42"},{"key":"28_CR12","unstructured":"Kender, J., Yeo, B.L.: On the structure and analysis of home videos. In: ACCV (2000)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Li, K., Oh, S., Perera, A., Fu, Y.: A videography analysis framework for video retrieval and summarization. In: BMVC (2012)","DOI":"10.5244\/C.26.126"},{"key":"28_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/978-3-319-10584-0_33","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Gygli","year":"2014","unstructured":"Gygli, M., Grabner, H., Riemenschneider, H., Gool, L.: Creating summaries from user videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 505\u2013520. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10584-0_33"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Poleg, Y., Arora, C., Peleg, S.: Temporal segmentation of egocentric videos. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.325"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, T.V., Xu, M., Gao, G., Kankanhalli, M., Tian, Q., Yan, S.: Static saliency vs. dynamic saliency: a comparative study. In: ACM MM (2013)","DOI":"10.1145\/2502081.2502128"},{"key":"28_CR17","first-page":"34","volume":"28","author":"N Ejaz","year":"2013","unstructured":"Ejaz, N., Mehmood, I., Baik, S.: Efficient visual attention based framework for extracting key frames from videos. Image Commun. 28, 34\u201344 (2013)","journal-title":"Image Commun."},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Itti, L., Dhavale, N., Pighin, F.: Realistic avatar eye and head animation using a neurobiological model of visual attention. In: Proceedings of the SPIE 48th Annual International Symposium on Optical Science and Technology, vol. 5200, pp. 64\u201378, August 2003","DOI":"10.1117\/12.512618"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: NIPS (2007)","DOI":"10.7551\/mitpress\/7503.003.0073"},{"issue":"7","key":"28_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/9.7.1","volume":"9","author":"H Seo","year":"2009","unstructured":"Seo, H., Milanfar, P.: Static and space-time visual saliency detection by self-resemblance. J. Vision 9(7), 1\u201327 (2009)","journal-title":"J. Vision"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Ma, Y.F., Lu, L., Zhang, H.J., Li, M.: A user attention model for video summarization. In: ACM MM (2002)","DOI":"10.1145\/641007.641116"},{"key":"28_CR22","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. 4713, pp. 405\u2013414. Springer, Heidelberg (2007). doi: 10.1007\/978-3-540-74936-3_41"},{"issue":"10","key":"28_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/10.10.28","volume":"10","author":"M Dorr","year":"2010","unstructured":"Dorr, M., Martinetz, T., Gegenfurtner, K.R., Barth, E.: Variability of eye movements when viewing dynamic natural scenes. J. Vision 10(10), 1\u201317 (2010)","journal-title":"J. Vision"},{"key":"28_CR24","unstructured":"Pilu, M.: On the use of attention clues for an autonomous wearable camera. Technical report HPL-2002-195, HP Laboratories Bristol (2003)"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Rallapalli, S., Ganesan, A., Padmanabhan, V., Chintalapudi, K., Qiu, L.: Enabling physical analytics in retail stores using smart glasses. In: MobiCom (2014)","DOI":"10.1145\/2639108.2639126"},{"key":"28_CR26","unstructured":"Nakamura, Y., Ohde, J., Ohta, Y.: Structuring personal activity records based on attention-analyzing videos from head mounted camera. In: ICPR (2000)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Cheatle, P.: Media content and type selection from always-on wearable video. In: ICPR (2004)","DOI":"10.1109\/ICPR.2004.1333937"},{"key":"28_CR28","unstructured":"Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: CVPR (2012)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Lu, Z., Grauman, K.: Story-driven summarization for egocentric video. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.350"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Aghazadeh, O., Sullivan, J., Carlsson, S.: Novelty detection from an egocentric perspective. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995731"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Hoshen, Y., Ben-Artzi, G., Peleg, S.: Wisdom of the crowd in egocentric video curation. In: CVPR Workshop (2014)","DOI":"10.1109\/CVPRW.2014.90"},{"key":"28_CR32","unstructured":"Park, H.S., Jain, E., Sheikh, Y.: 3D gaze concurrences from head-mounted cameras. In: NIPS (2012)"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Fathi, A., Hodgins, J., Rehg, J.: Social interactions: a first-person perspective. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Fathi, A., Farhadi, A., Rehg, J.: Understanding egocentric activities. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D.: Detecting activities of daily living in first-person camera views. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Damen, D., Leelasawassuk, T., Haines, O., Calway, A., Mayol-Cuevas, W.: You-do, i-learn: discovering task relevant objects and their modes of interaction from multi-user egocentric video. In: BMVC 2014 (2014)","DOI":"10.5244\/C.28.30"},{"key":"28_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-319-16814-2_12","volume-title":"Computer Vision \u2013 ACCV 2014","author":"B Soran","year":"2015","unstructured":"Soran, B., Farhadi, A., Shapiro, L.: Action recognition in the presence of one egocentric and multiple static cameras. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9007, pp. 178\u2013193. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-16814-2_12"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Kitani, K., Okabe, T., Sato, Y., Sugimoto, A.: Fast unsupervised ego-action learning for first-person sports video. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Spriggs, E., la Torre, F.D., Hebert, M.: Temporal segmentation and activity classification from first-person sensing. In: CVPR Workshop on Egocentric Vision (2009)","DOI":"10.1109\/CVPRW.2009.5204354"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y., Ye, Z., Rehg, J.: Delving into egocentric actions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298625"},{"issue":"1","key":"28_CR41","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s12559-010-9074-z","volume":"3","author":"PK Mital","year":"2011","unstructured":"Mital, P.K., Smith, T.J., Hill, R.L., Henderson, J.M.: Clustering of gaze during dynamic scene viewing is predicted by motion. Cogn. Comput. 3(1), 5\u201324 (2011)","journal-title":"Cogn. Comput."},{"key":"28_CR42","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint (2014). arXiv:1408.5093"},{"key":"28_CR43","unstructured":"Liu, C.: Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. Ph.D. thesis, Massachusetts Institute of Technology, May 2009"},{"key":"28_CR44","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in python. JMLR 12, 2825\u20132830 (2011)","journal-title":"JMLR"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46454-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T03:57:08Z","timestamp":1692503828000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46454-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464534","9783319464541"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46454-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"16 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}