{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:42:39Z","timestamp":1785336159020,"version":"3.55.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208929","type":"print"},{"value":"9783030208936","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-20893-6_21","type":"book-chapter","created":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:25:52Z","timestamp":1559013952000},"page":"330-346","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Visual Graphs from Motion (VGfM): Scene Understanding with Object Geometry Reasoning"],"prefix":"10.1007","author":[{"given":"Paul","family":"Gay","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Stuart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Del Bue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Bao, S.Y., Bagra, M., Chao, Y.W., Savarese, S.: Semantic structure from motion with points, regions, and objects. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2703\u20132710. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247992"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 211\u2013219. IEEE (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint \n                      arXiv:1409.1259\n                      \n                     (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"21_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-46484-8_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"CB Choy","year":"2016","unstructured":"Choy, C.B., Xu, D., Gwak, J.Y., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628\u2013644. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46484-8_38"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: Richly-annotated 3D reconstructions of indoor scenes. In: Computer Vision and Pattern Recognition (CVPR), pp. 2075\u20132084. IEEE (2017)","DOI":"10.1109\/CVPR.2017.261"},{"issue":"4","key":"21_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3054739","volume":"36","author":"Angela Dai","year":"2017","unstructured":"Dai, A., Nie\u00dfner, M., Zoll\u00f6fer, M., Izadi, S., Theobalt, C.: BundleFusion: real-time globally consistent 3D reconstruction using on-the-fly surface re-integration. Trans. Graph. (TOG) 36, 76a (2017)","journal-title":"ACM Transactions on Graphics"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., Lin, D.: Detecting visual relationships with deep relational networks. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3298\u20133308 (2017)","DOI":"10.1109\/CVPR.2017.352"},{"key":"21_CR8","unstructured":"Daniels, Z.A., Metaxas, D.N.: Scenarios: a new representation for complex scene understanding. arXiv preprint \n                      arXiv:1802.06117\n                      \n                     (2018)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for static human-object interactions. In: Computer Vision and Pattern Recognition Workshops (CVPR), pp. 9\u201316. IEEE (2010)","DOI":"10.1109\/CVPRW.2010.5543176"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Dong, J., Fei, X., Soatto, S.: Visual inertial semantic scene representation for 3D object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 782\u2013790. IEEE (2017)","DOI":"10.1109\/CVPR.2017.380"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Gay, P., Rubino, C., Bansal, V., Del Bue, A.: Probabilistic structure from motion with objects (PSfMO). In: International Conference on Computer Vision (ICCV), pp. 3075\u20133084. IEEE (2017)","DOI":"10.1109\/ICCV.2017.334"},{"issue":"9","key":"21_CR12","doi-asserted-by":"publisher","first-page":"1730","DOI":"10.1109\/TPAMI.2016.2613051","volume":"39","author":"C Hane","year":"2017","unstructured":"Hane, C., Zach, C., Cohen, A., Pollefeys, M.: Dense semantic 3D reconstruction. Pattern Anal. Mach. Intell. (PAMI) 39(9), 1730\u20131743 (2017)","journal-title":"Pattern Anal. Mach. Intell. (PAMI)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3668\u20133678. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Kang, K., Ouyang, W., Li, H., Wang, X.: Object detection from video tubelets with convolutional neural networks. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1744\u20131756. IEEE (2016)","DOI":"10.1109\/CVPR.2016.95"},{"issue":"1","key":"21_CR15","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (IJCV) 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., Wang, X.: Scene graph generation from objects, phrases and region captions. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1261\u20131270. IEEE (2017)","DOI":"10.1109\/ICCV.2017.142"},{"key":"21_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-319-46448-0_8","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Liang","year":"2016","unstructured":"Liang, X., Shen, X., Feng, J., Lin, L., Yan, S.: Semantic object parsing with graph LSTM. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 125\u2013143. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_8"},{"key":"21_CR18","unstructured":"Liao, W., Shuai, L., Rosenhahn, B., Yang, M.Y.: Natural language guided visual relationship detection. arXiv preprint \n                      arXiv:1711.06032\n                      \n                     (2017)"},{"key":"21_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"issue":"5","key":"21_CR20","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Computer Vision and Pattern Recognition (CVPR), pp. 1544\u20131556. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"21_CR22","doi-asserted-by":"publisher","unstructured":"Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Weakly-supervised learning of visual relations. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5189\u20135198 (2017). \n                      https:\/\/doi.org\/10.1109\/ICCV.2017.554\n                      \n                    . ISSN 2380-7504","DOI":"10.1109\/ICCV.2017.554"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Reddy, N.D., Singhal, P., Chari, V., Krishna, K.M.: Dynamic body VSLAM with semantic constraints. In: International Conference on Intelligent Robots (ICIR), pp. 1897\u20131904. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353626"},{"issue":"6","key":"21_CR24","first-page":"1281","volume":"40","author":"C Rubino","year":"2018","unstructured":"Rubino, C., Crocco, M., Del Bue, A.: 3D object localisation from multi-view image detections. Pattern Anal. Mach. Intell. (PAMI) 40(6), 1281\u20131294 (2018)","journal-title":"Pattern Anal. Mach. Intell. (PAMI)"},{"key":"21_CR25","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Neural Information Processing Systems NIPS, pp. 3856\u20133866 (2017)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Sengupta, S., Greveson, E., Shahrokni, A., Torr, P.H.S.: Urban 3D semantic modelling using stereo vision. In: International Conference on Robotics and Automation, pp. 580\u2013585. IEEE (2013)","DOI":"10.1109\/ICRA.2013.6630632"},{"key":"21_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \n                      arXiv:1409.1556\n                      \n                     (2014)"},{"issue":"6","key":"21_CR28","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1145\/2816795.2818094","volume":"34","author":"M Sung","year":"2015","unstructured":"Sung, M., Kim, V.G., Angst, R., Guibas, L.: Data-driven structural priors for shape completion. ACM Trans. Graph. (TOG) 34(6), 175 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Tripathi, S., Lipton, Z.C., Belongie, S.J., Nguyen, T.Q.: Context matters: refining object detection in video with recurrent neural networks. In: British Machine Vision Conference (BMVC), pp. 1723\u20131731. BMVA (2016)","DOI":"10.5244\/C.30.44"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Gupta, S., Fouhey, D., Efros, A.A., Malik, J.: Factoring shape, pose, and layout from the 2D image of a 3D scene. In: Computer Vision and Pattern Regognition (CVPR). IEEE (2018)","DOI":"10.1109\/CVPR.2018.00039"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3097\u20133106. IEEE (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: Conference on Computer Vision and Pattern Recognition CVPR, pp. 3294\u20133304. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4\u201312. IEEE (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"21_CR34","doi-asserted-by":"publisher","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1529\u20131537 (2015). \n                      https:\/\/doi.org\/10.1109\/ICCV.2015.179\n                      \n                    . ISSN 2380-7504","DOI":"10.1109\/ICCV.2015.179"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20893-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:44:24Z","timestamp":1559015064000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20893-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208929","9783030208936"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20893-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","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":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}