{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T10:08:26Z","timestamp":1743156506993,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695347"},{"type":"electronic","value":"9783030695354"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_39","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"641-653","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Point Proposal Based Instance Segmentation with Rectangular Masks for Robot Picking Task"],"prefix":"10.1007","author":[{"given":"Satoshi","family":"Ito","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susumu","family":"Kubota","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"39_CR1","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Neven, D., Brabandere, B.D., Proesmans, M., Gool, L.V.: Instance segmentation by jointly optimizing spatial embeddings and clustering bandwidth. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00904"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Sofiiuk, K., Barinova, O., Konushin, A.: Adaptis: adaptive instance selection network. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00745"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Danielczuk, M., et al..: Segmenting unknown 3D objects from real depth images using mask R-CNN trained on synthetic data. In: The IEEE International Conference on Robotics and Automation (ICRA) (2019)","DOI":"10.1109\/ICRA.2019.8793744"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Viet Pham, S.I., Kozakaya, T.: BiSeg: simultaneous instance segmentation and semantic segmentation with fully convolutional networks. In: The British Machine Vision Conference (BMVC) (2017)","DOI":"10.5244\/C.31.60"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X.: Mask scoring R-CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00657"},{"key":"39_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-030-58568-6_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Cheng","year":"2020","unstructured":"Cheng, T., Wang, X., Huang, L., Liu, W.: Boundary-preserving mask R-CNN. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XIV. LNCS, vol. 12359, pp. 660\u2013676. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_39"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: Pointrend: mage segmentation as rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"39_CR12","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28, pp. 91\u201399. Curran Associates, Inc. (2015)"},{"key":"39_CR13","unstructured":"Ying, H., Huang, Z., Liu, S., Shao, T., Zhou, K.: Embedmask: Embedding coupling for one-stage instance segmentation (2019)"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, Z., Shen, H., Cheng, B., Yang, L.: Centermask: single shot instance segmentation with point representation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00933"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: Centermask: real-time anchor-free instance segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"39_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-58452-8_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part I. LNCS, vol. 12346, pp. 282\u2013298. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_17"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"39_CR18","unstructured":"Fathi, A., et al.: Semantic instance segmentation via deep metric learning. CoRR abs\/1703.10277 (2017)"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"De Brabandere, B., Neven, D., Van Gool, L.: Semantic instance segmentation for autonomous driving. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2017)","DOI":"10.1109\/CVPRW.2017.66"},{"key":"39_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-030-58523-5_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Wang","year":"2020","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: SOLO: segmenting objects by locations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XVIII. LNCS, vol. 12363, pp. 649\u2013665. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_38"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"39_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part V. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01246-5_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Novotny","year":"2018","unstructured":"Novotny, D., Albanie, S., Larlus, D., Vedaldi, A.: Semi-convolutional operators for instance segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part I. LNCS, vol. 11205, pp. 89\u2013105. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_6"},{"key":"39_CR25","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)"},{"key":"39_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-50835-1_22","volume-title":"Advances in Visual Computing","author":"MA Rahman","year":"2016","unstructured":"Rahman, M.A., Wang, Y.: Optimizing intersection-over-union in deep neural networks for image segmentation. In: Bebis, G., et al. (eds.) ISVC 2016, Part I. LNCS, vol. 10072, pp. 234\u2013244. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-50835-1_22"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.308"},{"issue":"3","key":"39_CR29","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"39_CR30","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (ICLR) 2017 Conference Track (2017)"},{"key":"39_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"39_CR32","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","volume":"11","author":"A Buslaev","year":"2020","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information 11, 125 (2020)","journal-title":"Information"},{"key":"39_CR33","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"39_CR34","unstructured":"Massa, F., Girshick, R.: Mask R-CNN benchmark: Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch (2018). https:\/\/github.com\/facebookresearch\/maskrcnn-benchmark"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T16:16:44Z","timestamp":1614183404000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","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":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","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":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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 (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - 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 (provided by the conference organizers)"}},{"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 (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}