{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:51:29Z","timestamp":1777654289472,"version":"3.51.4"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012182","type":"print"},{"value":"9783030012199","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\/978-3-030-01219-9_34","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T10:23:51Z","timestamp":1538821431000},"page":"569-586","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6621-0356","authenticated-orcid":false,"given":"Bingbin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0529-0628","authenticated-orcid":false,"given":"Serena","family":"Yeung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0670-459X","authenticated-orcid":false,"given":"Edward","family":"Chou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6945-7768","authenticated-orcid":false,"given":"De-An","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8225-9793","authenticated-orcid":false,"given":"Juan Carlos","family":"Niebles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"34_CR1","unstructured":"Abu-El-Haija, S., et al.: YouTube-8M: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. arXiv preprint arXiv:1601.01705 (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"issue":"2","key":"34_CR5","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","journal-title":"Commun. ACM"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"34_CR7","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, HLT 2011, vol. 1, pp. 190\u2013200. Association for Computational Linguistics, Stroudsburg (2011). http:\/\/dl.acm.org\/citation.cfm?id=2002472.2002497"},{"key":"34_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"34_CR10","doi-asserted-by":"publisher","unstructured":"Feng, X., Perona, P.: Human action recognition by sequence of movelet codewords. In: Proceedings of First International Symposium on 3D Data Processing Visualization and Transmission, pp. 717\u2013721 (2002). https:\/\/doi.org\/10.1109\/TDPVT.2002.1024148","DOI":"10.1109\/TDPVT.2002.1024148"},{"key":"34_CR11","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Mikolov, T., et al.: Devise: a deep visual-semantic embedding model. In: NIPS (2013)"},{"issue":"11","key":"34_CR12","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","volume":"35","author":"A Gaidon","year":"2013","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal localization of actions with actoms. IEEE TPAMI 35(11), 2782\u20132795 (2013)","journal-title":"IEEE TPAMI"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. CoRR abs\/1705.08421 (2017). arXiv:1705.08421","DOI":"10.1109\/CVPR.2018.00633"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., et al.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"34_CR15","unstructured":"Han, W., et al.: Seq-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.C.: Localizing moments in video with natural language. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: end-to-end module networks for visual question answering. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"34_CR19","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/s11263-008-0142-8","volume":"80","author":"N \u0130kizler","year":"2008","unstructured":"\u0130kizler, N., Forsyth, D.A.: Searching for complex human activities with no visual examples. IJCV 80, 337\u2013357 (2008)","journal-title":"IJCV"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J.C., Mensink, T., Snoek, C.G.: Objects2action: classifying and localizing actions without any video example. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.521"},{"issue":"1","key":"34_CR21","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. TPAMI 35(1), 221\u2013231 (2013)","journal-title":"TPAMI"},{"key":"34_CR22","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes (2014). http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR, pp. 1988\u20131997. IEEE (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"34_CR26","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, vol. 1, pp. 423\u2013430. Association for Computational Linguistics (2003)","DOI":"10.3115\/1075096.1075150"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"34_CR29","unstructured":"Li, L.J., Su, H., Fei-Fei, L., Xing, E.P.: Object bank: a high-level image representation for scene classification & semantic feature sparsification. In: NIPS (2010)"},{"key":"34_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-642-35749-7_5","volume-title":"Trends and Topics in Computer Vision","author":"L-J Li","year":"2012","unstructured":"Li, L.-J., Su, H., Lim, Y., Fei-Fei, L.: Objects as attributes for scene classification. In: Kutulakos, K.N. (ed.) ECCV 2010. LNCS, vol. 6553, pp. 57\u201369. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35749-7_5"},{"key":"34_CR31","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.imavis.2016.11.004","volume":"59","author":"I Lillo","year":"2017","unstructured":"Lillo, I., Niebles, J.C., Soto, A.: Sparse composition of body poses and atomic actions for human activity recognition in RGB-D videos. Image Vis. Comput. 59, 63\u201375 (2017)","journal-title":"Image Vis. Comput."},{"key":"34_CR32","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: NIPS (2016)"},{"key":"34_CR33","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. arXiv preprint arXiv:1801.03150 (2018)"},{"key":"34_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-642-15552-9_29","volume-title":"Computer Vision \u2013 ECCV 2010","author":"JC Niebles","year":"2010","unstructured":"Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 392\u2013405. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15552-9_29"},{"key":"34_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-319-46493-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 744\u2013759. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_45"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"issue":"6","key":"34_CR37","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976\u2013990 (2010)","journal-title":"Image Vis. Comput."},{"key":"34_CR38","doi-asserted-by":"crossref","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc. Comput. Linguist. (2013)","DOI":"10.1162\/tacl_a_00207"},{"issue":"1","key":"34_CR39","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/s11263-016-0987-1","volume":"123","author":"A Rohrbach","year":"2017","unstructured":"Rohrbach, A., Torabi, A., Rohrbach, M., Tandon, N., Pal, C., Larochelle, H., Courville, A., Schiele, B.: Movie description. IJCV 123(1), 94\u2013120 (2017)","journal-title":"IJCV"},{"key":"34_CR40","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/s11263-015-0851-8","volume":"119","author":"M Rohrbach","year":"2016","unstructured":"Rohrbach, M., et al.: Recognizing fine-grained and composite activities using hand-centric features and script data. IJCV 119, 346\u2013373 (2016)","journal-title":"IJCV"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.J.: Action bank: a high-level representation of activity in video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"34_CR42","unstructured":"Schiele, B.: A database for fine grained activity detection of cooking activities. In: CVPR (2012)"},{"key":"34_CR43","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th ACM International Conference on Multimedia, MM 2007 (2007)","DOI":"10.1145\/1291233.1291311"},{"key":"34_CR44","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":"34_CR45","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"34_CR46","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ICLR (2015)"},{"key":"34_CR47","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"34_CR48","doi-asserted-by":"crossref","unstructured":"Socher, R., Karpathy, A., Le, Q.V., Manning, C.D., Ng, A.Y.: Grounded compositional semantics for finding and describing images with sentences. Trans. Assoc. Comput. Linguist. (2014)","DOI":"10.1162\/tacl_a_00177"},{"key":"34_CR49","unstructured":"Socher, R., Lin, C.C., Manning, C., Ng, A.Y.: Parsing natural scenes and natural language with recursive neural networks. In: ICML (2011)"},{"key":"34_CR50","doi-asserted-by":"crossref","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"34_CR51","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"34_CR52","unstructured":"Torabi, A., Tandon, N., Sigal, L.: Learning language-visual embedding for movie understanding with natural-language. arXiv preprint arXiv:1609.08124 (2016)"},{"key":"34_CR53","doi-asserted-by":"crossref","unstructured":"Tran, A., Cheong, L.F.: Two-stream flow-guided convolutional attention networks for action recognition. arXiv preprint arXiv:1708.09268 (2017)","DOI":"10.1109\/ICCVW.2017.368"},{"key":"34_CR54","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: C3D: generic features for video analysis. CoRR abs\/1412.0767 (2014). arXiv:1412.0767"},{"key":"34_CR55","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"34_CR56","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":"34_CR57","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.cviu.2010.10.002","volume":"115","author":"D Weinland","year":"2011","unstructured":"Weinland, D., Ronfard, R., Boyer, E.: A survey of vision-based methods for action representation, segmentation and recognition. Comput. Vis. Image Underst. 115, 224\u2013241 (2011)","journal-title":"Comput. Vis. Image Underst."},{"key":"34_CR58","doi-asserted-by":"crossref","unstructured":"Xiao, F., Sigal, L., Lee, Y.J.: Weakly-supervised visual grounding of phrases with linguistic structures. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.558"},{"key":"34_CR59","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"34_CR60","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"34_CR61","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"34_CR62","unstructured":"Yeung, S., Fathi, A., Fei-Fei, L.: VideoSET: video summary evaluation through text. arXiv preprint arXiv:1406.5824 (2014)"},{"key":"34_CR63","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.496"},{"key":"34_CR64","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1037\/0033-2909.127.1.3","volume":"127","author":"JM Zacks","year":"2001","unstructured":"Zacks, J.M., Tversky, B.: Event structure in perception and conception. Psychol. Bull. 127, 3\u201321 (2001)","journal-title":"Psychol. Bull."},{"key":"34_CR65","doi-asserted-by":"crossref","unstructured":"Zellers, R., Choi, Y.: Zero-shot activity recognition with verb attribute induction. arXiv preprint arXiv:1707.09468 (2017)","DOI":"10.18653\/v1\/D17-1099"},{"key":"34_CR66","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":"34_CR67","unstructured":"Zhou, L., Xu, C., Corso, J.J.: ProcNets: learning to segment procedures in untrimmed and unconstrained videos. CoRR abs\/1703.09788 (2017)"}],"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\/978-3-030-01219-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:47:39Z","timestamp":1775242059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_34","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":"7 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"}]}}