{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:14:31Z","timestamp":1766067271117,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030687922"},{"type":"electronic","value":"9783030687939"}],"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\/978-3-030-68793-9_31","type":"book-chapter","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T16:28:24Z","timestamp":1613838504000},"page":"423-436","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Top-1 CORSMAL Challenge 2020 Submission: Filling Mass Estimation Using Multi-modal Observations of Human-Robot Handovers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8879-587X","authenticated-orcid":false,"given":"Vladimir","family":"Iashin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1862-4853","authenticated-orcid":false,"given":"Francesca","family":"Palermo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6342-1345","authenticated-orcid":false,"given":"G\u00f6khan","family":"Solak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3835-9268","authenticated-orcid":false,"given":"Claudio","family":"Coppola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,21]]},"reference":[{"key":"31_CR1","unstructured":"The 2020 CORSMAL Challenge. Multi-modal fusion and learning for robotics. https:\/\/corsmal.eecs.qmul.ac.uk\/ICPR2020challenge.html. Accessed 22 Nov 2020"},{"issue":"2","key":"31_CR2","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123\u2013140 (1996). https:\/\/doi.org\/10.1007\/BF00058655","journal-title":"Mach. Learn."},{"key":"31_CR3","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS 2014 Workshop on Deep Learning, Dec 2014 (2014)"},{"issue":"12","key":"31_CR4","doi-asserted-by":"publisher","first-page":"e0144610","DOI":"10.1371\/journal.pone.0144610","volume":"10","author":"T Giannakopoulos","year":"2015","unstructured":"Giannakopoulos, T.: pyAudioAnalysis: an open-source python library for audio signal analysis. PLoS One 10(12), e0144610 (2015)","journal-title":"PLoS One"},{"key":"31_CR5","unstructured":"Griffith, S., Sukhoy, V., Wegter, T., Stoytchev, A.: Object categorization in the sink: learning behavior-grounded object categories with water. In: Proceedings of the 2012 ICRA Workshop on Semantic Perception, Mapping and Exploration. Citeseer (2012)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Hampali, S., Rad, M., Oberweger, M., Lepetit, V.: Honnotate: a method for 3D annotation of hand and object poses. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3196\u20133206 (2020)","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"31_CR8","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":"31_CR9","doi-asserted-by":"publisher","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952132","DOI":"10.1109\/ICASSP.2017.7952132"},{"issue":"8","key":"31_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7310\u20137311 (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Iashin, V., Rahtu, E.: A better use of audio-visual cues: dense video captioning with bi-modal transformer. In: British Machine Vision Conference (BMVC) (2020)","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Iashin, V., Rahtu, E.: Multi-modal dense video captioning. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 958\u2013959 (2020)","DOI":"10.1109\/CVPRW50498.2020.00487"},{"issue":"1","key":"31_CR14","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/protein\/13.1.15","volume":"13","author":"RD King","year":"2000","unstructured":"King, R.D., et al.: Is it better to combine predictions? Protein Eng. 13(1), 15\u201319 (2000)","journal-title":"Protein Eng."},{"key":"31_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Kokic, M., Kragic, D., Bohg, J.: Learning to estimate pose and shape of hand-held objects from RGB images. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3980\u20133987. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8967961"},{"key":"31_CR17","doi-asserted-by":"publisher","unstructured":"Liang, H., et al.: Making sense of audio vibration for liquid height estimation in robotic pouring. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5333\u20135339 (2019). https:\/\/doi.org\/10.1109\/IROS40897.2019.8968303","DOI":"10.1109\/IROS40897.2019.8968303"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Liang, H., et al.: Robust robotic pouring using audition and haptics. arXiv preprint arXiv:2003.00342 (2020)","DOI":"10.1109\/IROS45743.2020.9340859"},{"key":"31_CR19","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":"31_CR20","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. In: British Machine Vision Conference (2019)"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Schenck, C., Fox, D., Farhadi, A.: See the glass half full: reasoning about liquid containers, their volume and content. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1871\u20131880 (2017)","DOI":"10.1109\/ICCV.2017.207"},{"key":"31_CR22","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":"31_CR23","unstructured":"Phillips, C.J., Lecce, M., Daniilidis, K.: Seeing glassware: from edge detection to pose estimation and shape recovery. In: Robotics: Science and Systems, vol. 3 (2016)"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Sajjan, S., et al.: Clear grasp: 3D shape estimation of transparent objects for manipulation. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 3634\u20133642. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197518"},{"issue":"2","key":"31_CR25","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1109\/LRA.2020.2969200","volume":"5","author":"R Sanchez-Matilla","year":"2020","unstructured":"Sanchez-Matilla, R., et al.: Benchmark for human-to-robot handovers of unseen containers with unknown filling. IEEE Robot. Autom. Lett. 5(2), 1642\u20131649 (2020). https:\/\/doi.org\/10.1109\/LRA.2020.2969200","journal-title":"IEEE Robot. Autom. Lett."},{"key":"31_CR26","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"Statistics, L.B., Breiman, L.","year":"2001","unstructured":"Statistics, L.B., Breiman, L.: Random forests. Mach. Learn. 45, 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"31_CR28","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":"31_CR29","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 (CVPR) (June 2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1328\u20131338 (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"31_CR31","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 (2018)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"31_CR32","doi-asserted-by":"publisher","unstructured":"Xompero, A., Sanchez-Matilla, R., Modas, A., Frossard, P., Cavallaro, A.: Multi-view shape estimation of transparent containers. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2363\u20132367 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054112","DOI":"10.1109\/ICASSP40776.2020.9054112"},{"key":"31_CR33","doi-asserted-by":"publisher","unstructured":"Xompero, A., Sanchez-Matilla, R., Mazzon, R., Cavallaro, A.: CORSMAL containers manipulation (2020). https:\/\/doi.org\/10.17636\/101CORSMAL1, http:\/\/corsmal.eecs.qmul.ac.uk\/containers_manip.html","DOI":"10.17636\/101CORSMAL1"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68793-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,25]],"date-time":"2021-04-25T17:04:46Z","timestamp":1619370286000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68793-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030687922","9783030687939"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68793-9_31","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":"21 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPR2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpr2020.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}