{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:28:05Z","timestamp":1755998885988,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319466033"},{"type":"electronic","value":"9783319466040"}],"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\/978-3-319-46604-0_38","type":"book-chapter","created":{"date-parts":[[2016,9,17]],"date-time":"2016-09-17T03:31:55Z","timestamp":1474083115000},"page":"532-545","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["SEMBED: Semantic Embedding of Egocentric Action Videos"],"prefix":"10.1007","author":[{"given":"Michael","family":"Wray","sequence":"first","affiliation":[]},{"given":"Davide","family":"Moltisanti","sequence":"additional","affiliation":[]},{"given":"Walterio","family":"Mayol-Cuevas","sequence":"additional","affiliation":[]},{"given":"Dima","family":"Damen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,18]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J., Bojanowski, P., Agrawal, N., Laptev, I., Sivic, J., Lacoste-Julien, S.: Unsupervised learning from narrated instruction videos. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.495"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Bleser, G., Damen, D., Behera, A., Hendeby, G., Mura, K., Miezal, M., Gee, A., Petersen, N., Macaes, G., Domingues, H., Gorecky, D., Almeida, L., Mayol-Cuevas, W., Calways, A., Cohen, A., Hogg, D., Stricker, D.: Cognitive learning, monitoring and assistance of industrial workflows using egocentric sensor networks. PLOS ONE (2015)","DOI":"10.1371\/journal.pone.0127769"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C.H., Patel, V.M., Chellappa, R.: Matrix completion for resolving label ambiguity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7299038"},{"key":"38_CR4","unstructured":"Chen, D., Dolan, W.: Collecting highly parallel data for paraphrase evaluation. In: Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (2011)"},{"key":"38_CR5","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, ECCV (2004)"},{"key":"38_CR6","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)","DOI":"10.5244\/C.28.30"},{"key":"38_CR7","unstructured":"De La Torre, F., Hodgins, J., Bargteil, A., Martin, X., Macey, J., Collado, A., Beltran, P.: Guide to the Carnegie Mellon University Multimodal Activity (CMU-MMAC) database. Robotics Institute (2008)"},{"key":"38_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-642-33765-9_29","volume-title":"Computer Vision \u2013 ECCV 2012","author":"C Fang","year":"2012","unstructured":"Fang, C., Torresani, L.: Measuring image distances via embedding in a semantic manifold. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 402\u2013415. Springer, Heidelberg (2012)"},{"key":"38_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/978-3-642-33718-5_23","volume-title":"Computer Vision \u2013 ECCV 2012","author":"A Fathi","year":"2012","unstructured":"Fathi, A., Li, Y., Rehg, J.M.: Learning to recognize daily actions using gaze. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 314\u2013327. Springer, Heidelberg (2012)"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Fathi, A., Rehg, J.: Modeling actions through state changes. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.333"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.: Learning to recognize objects in egocentric activities. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"38_CR12","unstructured":"Ghosh, J., Lee, Y.J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: CVPR (2012)"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Krishnamoorthy, N., Malkarnenkar, G., Venugopalan, S., Mooney, R., Darrell, T., Saenko, K.: Youtube2text: Recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.337"},{"issue":"5","key":"38_CR14","doi-asserted-by":"crossref","first-page":"419","DOI":"10.3233\/IDA-2006-10503","volume":"10","author":"Eyke H\u00fcllermeier","year":"2006","unstructured":"H\u00fcllermeier, E., Beringer, J.: Learning from ambiguously labeled examples. In: Intelligent Data Analysis, pp. 419\u2013439 (2006)","journal-title":"Intelligent Data Analysis"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Ishihara, T., Kitani, K., Ma, W., Takagi, H., Asahawa, C.: Recognizing hand-object interactions in wearable camera videos. In: ICIP (2015)","DOI":"10.1109\/ICIP.2015.7351020"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Jin, Y., Khan, L., Wang, L., Awad, M.: Image annotations by combining multiple evidence & Wordnet. In: ACM international conference on Multimedia (2005)","DOI":"10.1145\/1101149.1101305"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Kitani, K., Okabe, T., Sato, Y., Sugimoto, A.: Fast unsupervised ego-action learning for first-person sports videos. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"38_CR18","unstructured":"Kuehne, H., Serre, T.: Towards a generative approach to activity recognition and segmentation. AXiv preprint \n                      arXiv:1509.01947\n                      \n                     (2015)"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Kumar, J., Li, Q., Kyal, S., Bernal, E., Bala, R.: On-the-fly hand detection training with application in egocentric action recognition. In: CVPRW (2015)","DOI":"10.1109\/CVPRW.2015.7301344"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Lade, P., Krishnan, N., Panchanathan, S.: Task prediction in cooking activities using hierarchical state space markov chain and object based task grouping. In: ISM (2010)","DOI":"10.1109\/ISM.2010.49"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Ye, Z., Rehg, J.: Delving into egocentric actions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Ma, M., Fan, H., Kitani, K.: Going deeper into first-person activity recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.209"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"McCandless, T., Grauman, K.: Object-centric spatio-temporal pyramids for egocentric activity recognition. In: BMVC (2013)","DOI":"10.5244\/C.27.30"},{"issue":"11","key":"38_CR24","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"AM George","year":"1995","unstructured":"George, A.M.: Wordnet: a lexical database for english. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"38_CR25","doi-asserted-by":"crossref","unstructured":"Moghimi, M., Azagra, P., Montesano, L., Murillo, A., Belongie, S.: Experiments on an rgb-d wearable vision system for egocentric activity recognition. In: CVPRW (2014)","DOI":"10.1109\/CVPRW.2014.94"},{"key":"38_CR26","unstructured":"Motwani, T., Mooney, R.: Improving video activity recognition using object recognition and text mining. In: ECAI (2012)"},{"issue":"1","key":"38_CR27","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/s11263-015-0815-z","volume":"115","author":"V Ordonez","year":"2015","unstructured":"Ordonez, V., Liu, W., Deng, J., Choi, Y., Berg, A., Berg, T.: Predicting entry-level categories. IJCV 115(1), 29\u201343 (2015)","journal-title":"IJCV"},{"key":"38_CR28","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":"38_CR29","doi-asserted-by":"crossref","unstructured":"Ren, X., Gu, C.: Figure-ground segmentation improves handled object recognition in egocentric video. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540074"},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Ryoo, M., Rothrock, B., Matthies, L.: Pooled motion features for first-person videos. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298691"},{"issue":"3","key":"38_CR31","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image classification with the fisher vector: theory and practice. IJCV 105(3), 222\u2013245 (2013)","journal-title":"IJCV"},{"key":"38_CR32","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: Integrated recognition, localization and detection using convolutional networks. ICLR (2013)"},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Singh, S., Arora, C., Jawahar, C.: First person action recognition using deep learned descriptors. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.287"},{"key":"38_CR34","doi-asserted-by":"crossref","unstructured":"Spriggs, E., De La Torre, F., Hebert, M.: Temporal segmentation and activity classification from first-person sensing. In: CVPRW (2009)","DOI":"10.1109\/CVPRW.2009.5204354"},{"key":"38_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1007\/978-3-642-17274-8_58","volume-title":"Advances in Visual Computing","author":"S Sundaram","year":"2010","unstructured":"Sundaram, S., Mayol-Cuevas, W.W.: Egocentric visual event classification with location-based priors. In: Bebis, G., et al. (eds.) ISVC 2010, Part II. LNCS, vol. 6454, pp. 596\u2013605. Springer, Heidelberg (2010)"},{"key":"38_CR36","doi-asserted-by":"crossref","unstructured":"Taralova, E., De La Torre, F., Hebert, M.: Source constrained clustering. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126462"},{"key":"38_CR37","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.: Action recognition by dense trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"38_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46604-0_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T00:50:38Z","timestamp":1602291038000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46604-0_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319466033","9783319466040"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46604-0_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"18 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"}]}}