{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:11:26Z","timestamp":1775243486530,"version":"3.50.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012458","type":"print"},{"value":"9783030012465","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\/978-3-030-01246-5_39","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:14:56Z","timestamp":1538756096000},"page":"656-672","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Joint Person Segmentation and Identification in Synchronized First- and Third-Person Videos"],"prefix":"10.1007","author":[{"given":"Mingze","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyou","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael S.","family":"Ryoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David J.","family":"Crandall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"39_CR1","unstructured":"http:\/\/www.gopro.com\/"},{"key":"39_CR2","unstructured":"http:\/\/www.spectacles.com\/"},{"key":"39_CR3","unstructured":"http:\/\/pytorch.org\/"},{"key":"39_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-319-46454-1_16","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Ardeshir","year":"2016","unstructured":"Ardeshir, S., Borji, A.: Ego2Top: matching viewers in egocentric and\u00a0top-view videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 253\u2013268. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_16"},{"key":"39_CR5","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv:1511.00561 (2015)"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: iCoseg: interactive co-segmentation with intelligent scribble guidance. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540080"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Chen, D.J., Chen, H.T., Chang, L.W.: Video object cosegmentation. In: ACMMM (2012)","DOI":"10.1145\/2393347.2396317"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv:1802.02611 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Wang, S., Yang, M.H.: SegFlow: joint learning for video object segmentation and optical flow. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Chiu, W.C., Fritz, M.: Multi-class video co-segmentation with a generative multi-video model. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.48"},{"key":"39_CR12","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":"39_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/978-3-642-15555-0_42","volume-title":"Computer Vision \u2013 ECCV 2010","author":"I Endres","year":"2010","unstructured":"Endres, I., Hoiem, D.: Category independent object proposals. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 575\u2013588. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_42"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Fan, C., et al.: Identifying first-person camera wearers in third-person videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.503"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Fu, H., Xu, D., Zhang, B., Lin, S.: Object-based multiple foreground video co-segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.405"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Guo, J., Cheong, L.F., Tan, R.T., Zhou, S.Z.: Consistent foreground co-segmentation. In: ACCV (2014)","DOI":"10.1007\/978-3-319-16817-3_16"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. arXiv:1703.06870 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Jang, W.D., Kim, C.S.: Online video object segmentation via convolutional trident network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.790"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Jun Koh, Y., Kim, C.S.: Primary object segmentation in videos based on region augmentation and reduction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.784"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Perazzi, F., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. arXiv:1612.02646 (2016)","DOI":"10.1109\/CVPR.2017.372"},{"key":"39_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"39_CR24","unstructured":"Lafayette Group: Survey of technology needs - body worn cameras. Technical report (2015)"},{"key":"39_CR25","unstructured":"LDV Capital: 45 billion cameras by 2022 fuel business opportunities. Technical report (2017)"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. arXiv:1611.07709 (2016)","DOI":"10.1109\/CVPR.2017.472"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Khoreva, A., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"39_CR30","unstructured":"Pinheiro, P.O., Collobert, R., Doll\u00e1r, P.: Learning to segment object candidates. In: NIPS (2015)"},{"key":"39_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/978-3-319-46448-0_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"PO Pinheiro","year":"2016","unstructured":"Pinheiro, P.O., Lin, T.-Y., Collobert, R., Doll\u00e1r, P.: Learning to refine object segments. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 75\u201391. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_5"},{"key":"39_CR32","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":"39_CR33","unstructured":"Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: CVPR (2006)"},{"key":"39_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-642-37444-9_2","volume-title":"Computer Vision \u2013 ACCV 2012","author":"JC Rubio","year":"2013","unstructured":"Rubio, J.C., Serrat, J., L\u00f3pez, A.: Video co-segmentation. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7725, pp. 13\u201324. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37444-9_2"},{"key":"39_CR35","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"39_CR36","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"39_CR37","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1109\/TPAMI.2013.230","volume":"36","author":"AWM Smeulders","year":"2014","unstructured":"Smeulders, A.W.M., Chu, D.M., Cucchiara, R., Calderara, S., Dehghan, A., Shah, M.: Visual tracking: an experimental survey. PAMI 36, 1442\u20131468 (2014)","journal-title":"PAMI"},{"key":"39_CR38","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. arXiv:1704.05737 (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"39_CR39","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. arXiv:1706.09364 (2017)","DOI":"10.5244\/C.31.116"},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Yonetani, R., Kitani, K.M., Sato, Y.: Ego-surfing first-person videos. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299183"},{"key":"39_CR41","doi-asserted-by":"crossref","unstructured":"Yoon, J.S., Rameau, F., Kim, J., Lee, S., Shin, S., Kweon, I.S.: Pixel-level matching for video object segmentation using convolutional neural networks. arXiv:1708.05137 (2017)","DOI":"10.1109\/ICCV.2017.238"},{"key":"39_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. arXiv:1612.01105 (2016)","DOI":"10.1109\/CVPR.2017.660"},{"key":"39_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, K., et al.: Learning view-invariant features for person identification in temporally synchronized videos taken by wearable cameras. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.311"},{"key":"39_CR44","unstructured":"Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future. arXiv:1610.02984 (2016)"}],"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\/978-3-030-01246-5_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:37:42Z","timestamp":1775241462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01246-5_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012458","9783030012465"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01246-5_39","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"}]}}