{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T17:10:16Z","timestamp":1732641016876,"version":"3.28.2"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Project 333 of Jiangsu Province"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s00138-024-01592-6","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T14:03:07Z","timestamp":1723471387000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial imitation learning-based network for category-level 6D object pose estimation"],"prefix":"10.1007","volume":"35","author":[{"given":"Shantong","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aryan","family":"Kaushik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"issue":"9","key":"1592_CR1","doi-asserted-by":"publisher","first-page":"6795","DOI":"10.1109\/TIM.2020.2976420","volume":"69","author":"B Cheng","year":"2020","unstructured":"Cheng, B., Wu, W., Tao, D., Mei, S., Mao, T., Cheng, J.: Random cropping ensemble neural network for image classification in a robotic arm grasping system. IEEE Trans. Instrument. Measure. 69(9), 6795\u20136806 (2020)","journal-title":"IEEE Trans. Instrument. Measure."},{"key":"1592_CR2","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s00138-012-0434-4","volume":"24","author":"R Subramanian","year":"2013","unstructured":"Subramanian, R., Spalding, E.P., Ferrier, N.J.: A high throughput robot system for machine vision based plant phenotype studies. Mach. Vis. Appl. 24, 619\u2013636 (2013)","journal-title":"Mach. Vis. Appl."},{"issue":"9","key":"1592_CR3","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1109\/TCSVT.2019.2950449","volume":"30","author":"F Tang","year":"2019","unstructured":"Tang, F., Wu, Y., Hou, X., Ling, H.: 3D mapping and 6D pose computation for real time augmented reality on cylindrical objects. IEEE Trans. Circuits Syst. Video Technol. 30(9), 2887\u20132899 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"1592_CR4","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1109\/TOH.2020.2967389","volume":"13","author":"SV Salazar","year":"2020","unstructured":"Salazar, S.V., Pacchierotti, C., de Tinguy, X., Maciel, A., Marchal, M.: Altering the stiffness, friction, and shape perception of tangible objects in virtual reality using wearable haptics. IEEE Trans. Haptics 13(1), 167\u2013174 (2020)","journal-title":"IEEE Trans. Haptics"},{"issue":"4","key":"1592_CR5","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.3233\/JIFS-201680","volume":"42","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Liang, J., Chen, L., Wang, Y., Gong, J.: Evaluation and prediction of free driving behavior type based on fuzzy comprehensive support vector machine. J. Intell. Fuzzy Syst. 42(4), 2863\u20132879 (2022)","journal-title":"J. Intell. Fuzzy Syst."},{"key":"1592_CR6","doi-asserted-by":"publisher","first-page":"2417","DOI":"10.1007\/s11063-020-10198-8","volume":"51","author":"S Sun","year":"2020","unstructured":"Sun, S., Liu, R., Du, Q., Sun, S.: Selective embedding with gated fusion for 6D object pose estimation. Neural Process. Lett. 51, 2417\u20132436 (2020)","journal-title":"Neural Process. Lett."},{"issue":"3","key":"1592_CR7","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s00138-023-01396-0","volume":"34","author":"J Liu","year":"2023","unstructured":"Liu, J., Mu, X., Liu, Z., Li, H.: Human skeleton behavior recognition model based on multi-object pose estimation with spatiotemporal semantics. Mach. Vis. Appl. 34(3), 44 (2023)","journal-title":"Mach. Vis. Appl."},{"key":"1592_CR8","doi-asserted-by":"crossref","unstructured":"Wang, C., Xu, D., Zhu, Y., Mart\u00edn-Mart\u00edn, R., Lu, C., Fei-Fei, L., Savarese, S.: Densefusion: 6d object pose estimation by iterative dense fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3343\u20133352 (2019)","DOI":"10.1109\/CVPR.2019.00346"},{"issue":"3","key":"1592_CR9","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1007\/s10462-020-09888-5","volume":"54","author":"G Du","year":"2021","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 (2021)","journal-title":"Artif. Intell. Rev."},{"key":"1592_CR10","doi-asserted-by":"crossref","unstructured":"Chen, K., Dou, Q.: Sgpa: Structure-guided prior adaptation for category-level 6d object pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2773\u20132782 (2021)","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"1592_CR11","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2020.01.085","volume":"396","author":"X Wu","year":"2020","unstructured":"Wu, X., Sahoo, D., Hoi, S.C.: Recent advances in deep learning for object detection. Neurocomputing 396, 39\u201364 (2020)","journal-title":"Neurocomputing"},{"key":"1592_CR12","doi-asserted-by":"crossref","unstructured":"Shi, B., Darrell, T., Wang, X.: Top-down visual attention from analysis by synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2102\u20132112 (2023)","DOI":"10.1109\/CVPR52729.2023.00209"},{"key":"1592_CR13","doi-asserted-by":"crossref","unstructured":"Yildirim, I., Siegel, M.H., Soltani, A.A., Chaudhari, S.R., Tenenbaum, J.B.: 3D shape perception integrates intuitive physics and analysis-by-synthesis. arXiv preprint arXiv:2301.03711 (2023)","DOI":"10.1038\/s41562-023-01759-7"},{"key":"1592_CR14","doi-asserted-by":"crossref","unstructured":"Dey, R., Boddeti, V.N.: 3DFaceFill: An analysis-by-synthesis approach to face completion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1586\u20131595 (2022)","DOI":"10.1109\/WACV51458.2022.00129"},{"key":"1592_CR15","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1007\/s00138-018-0951-x","volume":"29","author":"A Loesch","year":"2018","unstructured":"Loesch, A., Bourgeois, S., Gay-Bellile, V.: Localization of 3D objects using model-constrained SLAM. Mach. Vis. Appl. 29, 1041\u20131068 (2018)","journal-title":"Mach. Vis. Appl."},{"key":"1592_CR16","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: inerf: inverting neural radiance fields for pose estimation. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1323\u20131330 (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"1592_CR17","doi-asserted-by":"crossref","unstructured":"Jang, W., Agapito, L.: Codenerf: Disentangled neural radiance fields for object categories. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12949\u201312958 (2021)","DOI":"10.1109\/ICCV48922.2021.01271"},{"key":"1592_CR18","doi-asserted-by":"publisher","first-page":"13725","DOI":"10.1007\/s11042-019-08600-2","volume":"79","author":"K Cheng","year":"2020","unstructured":"Cheng, K., Tahir, R., Eric, L.K., Li, M.: An analysis of generative adversarial networks and variants for image synthesis on MNIST dataset. Multimedia Tools Appl. 79, 13725\u201313752 (2020)","journal-title":"Multimedia Tools Appl."},{"key":"1592_CR19","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":"1592_CR20","doi-asserted-by":"crossref","unstructured":"Chen, D., Li, J., Wang, Z., Xu, K.: Learning canonical shape space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11973\u201311982 (2020)","DOI":"10.1109\/CVPR42600.2020.01199"},{"issue":"6","key":"1592_CR21","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s00138-022-01338-2","volume":"33","author":"G Chen","year":"2022","unstructured":"Chen, G., Long, S., Yuan, Z., Zhu, W., Chen, Q., Wu, Y.: Ising granularity image analysis on VAE-GAN. Mach. Vis. Appl. 33(6), 81 (2022)","journal-title":"Mach. Vis. Appl."},{"key":"1592_CR22","doi-asserted-by":"crossref","unstructured":"Di, Y., Zhang, R., Lou, Z., Manhardt, F., Ji, X., Navab, N., Tombari, F.: Gpv-pose: Category-level object pose estimation via geometry-guided point-wise voting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6781\u20136791 (2022)","DOI":"10.1109\/CVPR52688.2022.00666"},{"key":"1592_CR23","doi-asserted-by":"crossref","unstructured":"Lin, J., Wei, Z., Li, Z., Xu, S., Jia, K., Li, Y.: Dualposenet: category-level 6d object pose and size estimation using dual pose network with refined learning of pose consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3560\u20133569 (2021)","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"1592_CR24","doi-asserted-by":"crossref","unstructured":"Wang, C., Mart\u00edn-Mart\u00edn, R., Xu, D., Lv, J., Lu, C., Fei-Fei, L., Zhu, Y.: 6-pack: category-level 6d pose tracker with anchor-based keypoints. In: 2020 IEEE International Conference on Robotics and Automation, pp. 10059\u201310066 (2020)","DOI":"10.1109\/ICRA40945.2020.9196679"},{"issue":"4","key":"1592_CR25","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1109\/TMM.2016.2629282","volume":"19","author":"Q Mao","year":"2016","unstructured":"Mao, Q., Rao, Q., Yu, Y., Dong, M.: Hierarchical Bayesian theme models for multipose facial expression recognition. IEEE Trans. Multimedia 19(4), 861\u2013873 (2016)","journal-title":"IEEE Trans. Multimedia"},{"key":"1592_CR26","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.compag.2019.02.005","volume":"158","author":"A Wang","year":"2019","unstructured":"Wang, A., Zhang, W., Wei, X.: A review on weed detection using ground-based machine vision and image processing techniques. Comput. Electronics Agric. 158, 226\u2013240 (2019)","journal-title":"Comput. Electronics Agric."},{"key":"1592_CR27","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Shmelkov, K., Mairal, J., Schmid, C.: Blitznet: A real-time deep network for scene understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4154\u20134162 (2017)","DOI":"10.1109\/ICCV.2017.447"},{"key":"1592_CR28","doi-asserted-by":"crossref","unstructured":"Krull, A., Brachmann, E., Michel, F., Yang, M. Y., Gumhold, S., Rother, C.: Learning analysis-by-synthesis for 6D pose estimation in RGB-D images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 954\u2013962 (2015)","DOI":"10.1109\/ICCV.2015.115"},{"key":"1592_CR29","doi-asserted-by":"crossref","unstructured":"Chen, X., Dong, Z., Song, J., Geiger, A., Hilliges, O.: Category level object pose estimation via neural analysis-by-synthesis. In: Proceedings of the European Conference on Computer Vision, pp. 139\u2013156 (2020)","DOI":"10.1007\/978-3-030-58574-7_9"},{"key":"1592_CR30","doi-asserted-by":"crossref","unstructured":"Guo, J., Zhong, F., Xiong, R., Liu, Y., Wang, Y., Liao, Y.: A visual navigation perspective for category-level object pose estimation. In: European Conference on Computer Vision, pp. 123\u2013141 (2022)","DOI":"10.1007\/978-3-031-20068-7_8"},{"issue":"1","key":"1592_CR31","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"issue":"2","key":"1592_CR32","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1109\/COMST.2018.2888904","volume":"21","author":"J Wang","year":"2018","unstructured":"Wang, J., Liu, J., Kato, N.: Networking and communications in autonomous driving: a survey. IEEE Commun. Surv. Tutorials. 21(2), 1243\u20131274 (2018)","journal-title":"IEEE Commun. Surv. Tutorials."},{"issue":"11","key":"1592_CR33","doi-asserted-by":"publisher","first-page":"6443","DOI":"10.1109\/TNNLS.2021.3080261","volume":"33","author":"Y Cai","year":"2021","unstructured":"Cai, Y., Dai, L., Wang, H., Chen, L., Li, Y.: DLnet with training task conversion stream for precise semantic segmentation in actual traffic scene. IEEE Trans. Neural Netw. Learn. Syst. 33(11), 6443\u20136457 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1592_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, W., Queralta, J.P., Westerlund, T.: Sim-to-real transfer in deep reinforcement learning for robotics: a survey. In: IEEE Symposium Series on Computational Intelligence, pp. 737\u2013744 (2020)","DOI":"10.1109\/SSCI47803.2020.9308468"},{"issue":"8","key":"1592_CR35","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao, Q., Dong, M., Huang, Z., Zhan, Y.: Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans. Multimedia 16(8), 2203\u20132213 (2014)","journal-title":"IEEE Trans. Multimedia"},{"key":"1592_CR36","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Kitani, K.: Ego-pose estimation and forecasting as real-time pd control. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10082\u201310092 (2019)","DOI":"10.1109\/ICCV.2019.01018"},{"key":"1592_CR37","doi-asserted-by":"crossref","unstructured":"Wang, B., Adeli, E., Chiu, H.K., Huang, D.A., Niebles, J.C.: Imitation learning for human pose prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7124\u20137133 (2019)","DOI":"10.1109\/ICCV.2019.00722"},{"key":"1592_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106795","volume":"97","author":"G Zuo","year":"2020","unstructured":"Zuo, G., Zhao, Q., Chen, K., Li, J., Gong, D.: Off-policy adversarial imitation learning for robotic tasks with low-quality demonstrations. Appl. Soft Comput. 97, 106795 (2020)","journal-title":"Appl. Soft Comput."},{"key":"1592_CR39","doi-asserted-by":"crossref","unstructured":"Bhattacharyya, R., Wulfe, B., Phillips, D.J., Kuefler, A., Morton, J., Senanayake, R., Kochenderfer, M.J.: Modeling human driving behavior through generative adversarial imitation learning. IEEE Trans. Intell. Transp. Syst. 24(3), 2874\u20132887 (2022)","DOI":"10.1109\/TITS.2022.3227738"},{"key":"1592_CR40","first-page":"20154","volume":"33","author":"K Schwarz","year":"2020","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: Graf: Generative radiance fields for 3d-aware image synthesis. Adv. Neural Inf. Process. Syst. 33, 20154\u201320166 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1592_CR41","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations, pp. 11\u201330 (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"1592_CR42","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.: Foundationpose: Unified 6d pose estimation and tracking of novel objects, In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17868\u201317879 (2024)","DOI":"10.1109\/CVPR52733.2024.01692"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01592-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01592-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01592-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T16:35:43Z","timestamp":1732638943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01592-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["1592"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01592-6","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"31 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"109"}}