{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:03:32Z","timestamp":1784552612301,"version":"3.55.0"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012243","type":"print"},{"value":"9783030012250","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01225-0_44","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T04:39:54Z","timestamp":1538973594000},"page":"753-771","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":231,"title":["Scaling Egocentric Vision: The \"Equation missing\" Dataset"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8804-6238","authenticated-orcid":false,"given":"Dima","family":"Damen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hazel","family":"Doughty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonino","family":"Furnari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelos","family":"Kazakos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Moltisanti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Munro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toby","family":"Perrett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Will","family":"Price","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Wray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"44_CR1","unstructured":"Abu-El-Haija, S., et al.: YouTube-8M: a large-scale video classification benchmark. In: CoRR (2016)"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Alletto, S., Serra, G., Calderara, S., Cucchiara, R.: Understanding social relationships in egocentric vision. Pattern Recogn. (2015)","DOI":"10.1016\/j.patcog.2015.06.006"},{"key":"44_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Banerjee, S., Pedersen, T.: An adapted lesk algorithm for word sense disambiguation using wordnet. In: CICLing (2002)","DOI":"10.1007\/3-540-45715-1_11"},{"key":"44_CR5","unstructured":"Carnegie Mellon University: CMU sphinx. https:\/\/cmusphinx.github.io\/"},{"key":"44_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":"44_CR7","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual Dialog. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"44_CR8","unstructured":"De La Torre, F., et al.: Guide to the carnegie mellon university multimodal activity (CMU-MMAC) database. In: Robotics Institute (2008)"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Doughty, H., Damen, D., Mayol-Cuevas, W.: Who\u2019s better? who\u2019s best? Pairwise deep ranking for skill determination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00634"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"44_CR12","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":"44_CR13","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. LNCS, vol. 7572, pp. 314\u2013327. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_23"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Fouhey, D.F., Kuo, W.c., Efros, A.A., Malik, J.: From lifestyle vlogs to everyday interactions. arXiv preprint arXiv:1712.02310 (2017)","DOI":"10.1109\/CVPR.2018.00524"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Furnari, A., Battiato, S., Grauman, K., Farinella, G.M.: Next-active-object prediction from egocentric videos. JVCIR (2017)","DOI":"10.1016\/j.jvcir.2017.10.004"},{"key":"44_CR16","unstructured":"Georgia Tech: Extended GTEA Gaze+ (2018). http:\/\/webshare.ipat.gatech.edu\/coc-rim-wall-lab\/web\/yli440\/egtea_gp"},{"key":"44_CR17","unstructured":"Google: Google cloud speech api. https:\/\/cloud.google.com\/speech"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"44_CR19","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":"44_CR20","unstructured":"Heidarivincheh, F., Mirmehdi, M., Damen, D.: Action completion: a temporal model for moment detection. In: BMVC (2018)"},{"key":"44_CR21","unstructured":"Huang, J., et al.: Tensorflow Object Detection API. https:\/\/github.com\/tensorflow\/models\/tree\/master\/research\/object_detection"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"44_CR23","unstructured":"IBM: IBM watson speech to text. https:\/\/www.ibm.com\/watson\/services\/speech-to-text"},{"key":"44_CR24","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"44_CR25","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Joint learning of object and action detectors. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.219"},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"44_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"44_CR28","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"44_CR29","unstructured":"Lee, Y., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: CVPR (2012)"},{"key":"44_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"44_CR31","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Miller, G.: WordNet: a lexical database for English. In: CACM (1995)","DOI":"10.3115\/1075812.1075938"},{"key":"44_CR33","doi-asserted-by":"crossref","unstructured":"Moltisanti, D., Wray, M., Mayol-Cuevas, W., Damen, D.: Trespassing the boundaries: Labeling temporal bounds for object interactions in egocentric video. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.314"},{"key":"44_CR34","doi-asserted-by":"crossref","unstructured":"Nair, A., et al.: Combining self-supervised learning and imitation for vision-based rope manipulation. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"44_CR35","doi-asserted-by":"crossref","unstructured":"Park, H.S., Hwang, J.J., Niu, Y., Shi, J.: Egocentric future localization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.508"},{"key":"44_CR36","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":"44_CR37","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"44_CR38","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"44_CR39","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"44_CR40","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Matthies, L.: First-person activity recognition: what are they doing to me? In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.352"},{"key":"44_CR41","unstructured":"Sigurdsson, G.A., Gupta, A., Schmid, C., Farhadi, A., Alahari, K.: Charades-ego: a large-scale dataset of paired third and first person videos. In: ArXiv (2018)"},{"key":"44_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"44_CR43","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"44_CR44","doi-asserted-by":"crossref","unstructured":"Stein, S., McKenna, S.: Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: UbiComp (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"44_CR45","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"44_CR46","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"44_CR47","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"44_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"44_CR49","unstructured":"Yamaguchi, K.: Bbox-annotator. https:\/\/github.com\/kyamagu\/bbox-annotator"},{"key":"44_CR50","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., Fei-Fei, L.: Every moment counts: dense detailed labeling of actions in complex videos. IJCV (2018)","DOI":"10.1007\/s11263-017-1013-y"},{"key":"44_CR51","unstructured":"Yuanjun, X.: PyTorch Temporal Segment Network (2017). https:\/\/github.com\/yjxiong\/tsn-pytorch"},{"key":"44_CR52","doi-asserted-by":"crossref","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. Pattern Recogn. (2007)","DOI":"10.1109\/ICCV.2007.4408983"},{"key":"44_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, T., McCarthy, Z., Jow, O., Lee, D., Goldberg, K., Abbeel, P.: Deep imitation learning for complex manipulation tasks from virtual reality teleoperation. In: ICRA (2018)","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"44_CR54","unstructured":"Zhao, H., Yan, Z., Wang, H., Torresani, L., Torralba, A.: SLAC: a sparsely labeled dataset for action classification and localization. arXiv preprint arXiv:1712.09374 (2017)"},{"key":"44_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"44_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. arXiv preprint arXiv:1703.09788 (2017)","DOI":"10.1609\/aaai.v32i1.12342"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01225-0_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:54:21Z","timestamp":1775242461000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01225-0_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012243","9783030012250"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.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"}]}}