{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:22:45Z","timestamp":1778084565390,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197680","type":"print"},{"value":"9783031197697","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19769-7_7","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T11:40:06Z","timestamp":1666438806000},"page":"106-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Fusing Local Similarities for\u00a0Retrieval-Based 3D Orientation Estimation of\u00a0Unseen Objects"],"prefix":"10.1007","author":[{"given":"Chen","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinlin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathieu","family":"Salzmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Balntas, V., Doumanoglou, A., Sahin, C., Sock, J., Kouskouridas, R., Kim, T.K.: Pose guided RGBD feature learning for 3d object pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3856\u20133864 (2017)","DOI":"10.1109\/ICCV.2017.416"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-319-10605-2_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"E Brachmann","year":"2014","unstructured":"Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6D object pose estimation using 3D object coordinates. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 536\u2013551. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_35"},{"key":"7_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Jia, X., Chang, H.J., Duan, J., Shen, L., Leonardis, A.: FS-net: fast shape-based network for category-level 6d object pose estimation with decoupled rotation mechanism. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1581\u20131590 (2021)","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"7_CR6","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"issue":"10","key":"7_CR7","doi-asserted-by":"publisher","first-page":"1284","DOI":"10.1177\/0278364911401765","volume":"30","author":"A Collet","year":"2011","unstructured":"Collet, A., Martinez, M., Srinivasa, S.S.: The moped framework: object recognition and pose estimation for manipulation. Int. J. Robot. Res. 30(10), 1284\u20131306 (2011)","journal-title":"Int. J. Robot. Res."},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"issue":"3","key":"7_CR9","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1007\/s10462-020-09888-5","volume":"54","author":"G Du","year":"2020","unstructured":"Du, G., Wang, K., Lian, S., Zhao, K.: Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review. Artif. Intell. Rev. 54(3), 1677\u20131734 (2020). https:\/\/doi.org\/10.1007\/s10462-020-09888-5","journal-title":"Artif. Intell. Rev."},{"issue":"6","key":"7_CR10","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","volume-title":"Computer Vision \u2013 ACCV 2012","author":"S Hinterstoisser","year":"2013","unstructured":"Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548\u2013562. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Hodan, T., Haluza, P., Obdr\u017e\u00e1lek, \u0160., Matas, J., Lourakis, M., Zabulis, X.: T-less: an RGB-D dataset for 6D pose estimation of texture-less objects. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 880\u2013888. IEEE (2017)","DOI":"10.1109\/WACV.2017.103"},{"key":"7_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/978-3-319-49409-8_52","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"T Hoda\u0148","year":"2016","unstructured":"Hoda\u0148, T., Matas, J., Obdr\u017e\u00e1lek, \u0160: On evaluation of 6D object pose estimation. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 606\u2013619. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_52"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Hu, Y., Fua, P., Wang, W., Salzmann, M.: Single-stage 6d object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2930\u20132939 (2020)","DOI":"10.1109\/CVPR42600.2020.00300"},{"key":"7_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, H., Yi, L., Guibas, L.J., Abbott, A.L., Song, S.: Category-level articulated object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3706\u20133715 (2020)","DOI":"10.1109\/CVPR42600.2020.00376"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, G., Ji, X., Xiang, Y., Fox, D.: DeepIM: deep iterative matching for 6D pose estimation. In: Proceedings of the European Conference on Computer Vision, pp. 683\u2013698 (2018)","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"7_CR21","unstructured":"Manuelli, L., Gao, W., Florence, P., Tedrake, R.: KPAM: keypoint affordances for category-level robotic manipulation. arXiv preprint arXiv:1903.06684 (2019)"},{"issue":"12","key":"7_CR22","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1109\/TVCG.2015.2513408","volume":"22","author":"E Marchand","year":"2015","unstructured":"Marchand, E., Uchiyama, H., Spindler, F.: Pose estimation for augmented reality: a hands-on survey. IEEE Trans. Visual. Comput. Graph. 22(12), 2633\u20132651 (2015)","journal-title":"IEEE Trans. Visual. Comput. Graph."},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Park, K., Mousavian, A., Xiang, Y., Fox, D.: LatentFusion: end-to-end differentiable reconstruction and rendering for unseen object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10710\u201310719 (2020)","DOI":"10.1109\/CVPR42600.2020.01072"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: PVNet: pixel-wise voting network for 6DoF pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4561\u20134570 (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"key":"7_CR25","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"7_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., et al.: Multi-path learning for object pose estimation across domains. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 13916\u201313925 (2020)","DOI":"10.1109\/CVPR42600.2020.01393"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Marton, Z.C., Durner, M., Brucker, M., Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: Proceedings of the European Conference on Computer Vision, pp. 699\u2013715 (2018)","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"7_CR29","unstructured":"Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. arXiv preprint arXiv:1809.10790 (2018)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Vaze, S., Han, K., Vedaldi, A., Zisserman, A.: Generalized category discovery. arXiv preprint arXiv:2201.02609 (2022)","DOI":"10.1109\/CVPR52688.2022.00734"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: 6-pack: category-level 6D pose tracker with anchor-based keypoints. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 10059\u201310066. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196679"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Densefusion: 6D object pose estimation by iterative dense fusion. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp. 3343\u20133352 (2019)","DOI":"10.1109\/CVPR.2019.00346"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Wang, G., Manhardt, F., Tombari, F., Ji, X.: GDR-Net: geometry-guided direct regression network for monocular 6d object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16611\u201316621 (2021)","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Wohlhart, P., Lepetit, V.: Learning descriptors for object recognition and 3D pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3109\u20133118 (2015)","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Du, Y., Marlet, R.: PoseContrast: class-agnostic object viewpoint estimation in the wild with pose-aware contrastive learning. In: 2021 International Conference on 3D Vision (3DV), pp. 74\u201384. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00018"},{"key":"7_CR38","unstructured":"Xiao, Y., Qiu, X., Langlois, P.A., Aubry, M., Marlet, R.: Pose from shape: deep pose estimation for arbitrary 3D objects. arXiv preprint arXiv:1906.05105 (2019)"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Xu, D., Anguelov, D., Jain, A.: PointFusion: deep sensor fusion for 3D bounding box estimation. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 244\u2013253 (2018)","DOI":"10.1109\/CVPR.2018.00033"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, M., et al.: Single image 3D object detection and pose estimation for grasping. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 3936\u20133943. IEEE (2014)","DOI":"10.1109\/ICRA.2014.6907430"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19769-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T10:07:15Z","timestamp":1728209235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19769-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197680","9783031197697"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19769-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.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 (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"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 (provided by the conference organizers)"}},{"value":"3.21","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":"3.91","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)"}}]}}