{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:08:35Z","timestamp":1766138915996,"version":"build-2065373602"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T00:00:00Z","timestamp":1728950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T00:00:00Z","timestamp":1728950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["2306029","62076024"],"award-info":[{"award-number":["2306029","62076024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62006018","U22B2055"],"award-info":[{"award-number":["62006018","U22B2055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J of Soc Robotics"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s12369-024-01176-4","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T22:01:53Z","timestamp":1728943313000},"page":"2097-2106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Understanding Dynamic Auditory and Tactile Perception for Water Filling Level Estimation"],"prefix":"10.1007","volume":"17","author":[{"given":"Xinyuan","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minshu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8538-8571","authenticated-orcid":false,"given":"Wanlin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu-Cheng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,15]]},"reference":[{"key":"1176_CR1","doi-asserted-by":"publisher","unstructured":"Wang H, Zhu C, Ma Z, Oh C (2022) Improving generalization of deep networks for estimating physical properties of containers and fillings. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, pp 9147\u20139151. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747349","DOI":"10.1109\/ICASSP43922.2022.9747349"},{"key":"1176_CR2","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TASLP.2022.3226330","volume":"31","author":"X Qian","year":"2022","unstructured":"Qian X, Wang Z, Wang J, Guan G, Li H (2022) Audio-visual cross-attention network for robotic speaker tracking. IEEE\/ACM Trans Audio, Speech, Language Process 31:550\u2013562","journal-title":"IEEE\/ACM Trans Audio, Speech, Language Process"},{"key":"1176_CR3","doi-asserted-by":"publisher","unstructured":"Unhelkar VV, Perez J, Boerkoel JC, Bix J, Bartscher S, Shah JA (2014) Towards control and sensing for an autonomous mobile robotic assistant navigating assembly lines. In: 2014 IEEE International Conference on Robotics and Automation (ICRA). https:\/\/doi.org\/10.1109\/icra.2014.6907464","DOI":"10.1109\/icra.2014.6907464"},{"key":"1176_CR4","doi-asserted-by":"crossref","unstructured":"Gleeson B, MacLean K, Haddadi A, Croft E, Alcazar J (2013) Gestures for industry: intuitive human-robot communication from human observation","DOI":"10.1109\/HRI.2013.6483609"},{"issue":"2","key":"1176_CR5","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1023\/b:auro.0000016865.35796.e9","volume":"16","author":"B Graf","year":"2004","unstructured":"Graf B, Hans M, Schraft RD (2004) Care-O-bot II-development of a next generation robotic home assistant. Auton Robots 16(2):193\u2013205. https:\/\/doi.org\/10.1023\/b:auro.0000016865.35796.e9","journal-title":"Auton Robots"},{"key":"1176_CR6","doi-asserted-by":"publisher","unstructured":"Micire M, Fong T, Morse T, Park E, Provencher C, Smith E, To V, Torres RJ, Wheeler DW, Mittman D (2013) Smart spheres: a telerobotic free-flyer for intravehicular activities in space. In: AIAA SPACE 2013 Conference and Exposition. https:\/\/doi.org\/10.2514\/6.2013-5338","DOI":"10.2514\/6.2013-5338"},{"key":"1176_CR7","doi-asserted-by":"publisher","unstructured":"Diftler MA, Permenter FA, Hargrave BK, Platt R, Savely RT, Ambrose RO, Mehling JS, Abdallah ME, Radford NA, Bridgwater LB, Sanders AM, Askew RS, Linn DM, Yamokoski JD (2011) Robonaut 2\u2014the first humanoid robot in space. In: 2011 IEEE International Conference on Robotics and Automation. https:\/\/doi.org\/10.1109\/icra.2011.5979830","DOI":"10.1109\/icra.2011.5979830"},{"key":"1176_CR8","doi-asserted-by":"publisher","unstructured":"Bualat M, Barlow J, Fong T, Provencher C, Smith T (2015) Astrobee: Developing a free-flying robot for the international space station. In: AIAA SPACE 2015 Conference and Exposition. https:\/\/doi.org\/10.2514\/6.2015-4643","DOI":"10.2514\/6.2015-4643"},{"key":"1176_CR9","doi-asserted-by":"publisher","unstructured":"Matsubara T, Otsuki S, Wada Y, Matsuo H, Komatsu T, Iioka Y, Sugiura K, Saito H (2022) Shared transformer encoder with mask-based 3d model estimation for container mass estimation. In: Proceedings of International Conference on Audio, Speech and Signal Processing, pp 9142\u20139146 . https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747110","DOI":"10.1109\/ICASSP43922.2022.9747110"},{"key":"1176_CR10","doi-asserted-by":"crossref","unstructured":"Modas A, Xompero A, Sanchez-Matilla R, Frossard P, Cavallaro A (2021) Improving filling level classification with adversarial training. In: Proceedings of IEEE International Conference on Image Processing. IEEE, pp 829\u2013833","DOI":"10.1109\/ICIP42928.2021.9506112"},{"key":"1176_CR11","doi-asserted-by":"crossref","unstructured":"Do C, Burgard W (2018) Accurate pouring with an autonomous robot using an rgb-d camera. arXiv:1810.03303","DOI":"10.1007\/978-3-030-01370-7_17"},{"key":"1176_CR12","doi-asserted-by":"publisher","unstructured":"Apicella T, Slavic G, Ragusa E, Gastaldo P, Marcenaro L (2022) Container localisation and mass estimation with an rgb-d camera. In: Proceedings of International Conference Audio, Speech, Signal Processing, pp 9152\u20139155 . https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747134","DOI":"10.1109\/ICASSP43922.2022.9747134"},{"key":"1176_CR13","first-page":"529","volume":"87","author":"S Clarke","year":"2018","unstructured":"Clarke S, Rhodes T, Atkeson CG, Kroemer O (2018) Learning audio feedback for estimating amount and flow of granular material. Proc of Mach Learn Res 87:529\u2013550","journal-title":"Proc of Mach Learn Res"},{"key":"1176_CR14","doi-asserted-by":"publisher","unstructured":"Liang H, Li S, Ma X, Hendrich N, Gerkmann T, Sun F, Zhang J (2019) Making sense of audio vibration for liquid height estimation in robotic pouring. In: Proceedings of International Conference on Intelligent Robots and Systems, pp 5333\u20135339 . https:\/\/doi.org\/10.1109\/IROS40897.2019.8968303","DOI":"10.1109\/IROS40897.2019.8968303"},{"key":"1176_CR15","doi-asserted-by":"publisher","unstructured":"Donaher S, Xompero A, Cavallaro A (2021) Audio classification of the content of food containers and drinking glasses. In: Proceedings of European Signal Processing Conference, pp 591\u2013595 . https:\/\/doi.org\/10.23919\/EUSIPCO54536.2021.9616206","DOI":"10.23919\/EUSIPCO54536.2021.9616206"},{"key":"1176_CR16","doi-asserted-by":"publisher","unstructured":"Wilson J, Sterling A, Lin MC (2019) Analyzing liquid pouring sequences via audio-visual neural networks. In: Proceedings of International Conference on Intelligent Robots and Systems, pp 7702\u20137709. https:\/\/doi.org\/10.1109\/IROS40897.2019.8968118","DOI":"10.1109\/IROS40897.2019.8968118"},{"key":"1176_CR17","unstructured":"Yang D-Z, Xu JL J-M, Xia S-H (2016) Reliable mute model and speech activity detection in speaker logs. In: Journal of Zhejiang University (Engineering Science), vol 50. pp 151\u2013157"},{"key":"1176_CR18","first-page":"1","volume":"40","author":"J Yang","year":"2020","unstructured":"Yang J, Li Z, Su P (2020) Review of speech segmentation and endpoint detection. J Comput Appl 40:1\u20137","journal-title":"J Comput Appl"},{"key":"1176_CR19","doi-asserted-by":"publisher","unstructured":"Burns A, Xiang S, Lee D, Jackel L, Song S, Isler V (2022) Look and listen: A multi-sensory pouring network and dataset for granular media from human demonstrations. In: Proceedings of International Conference on Robotics and Automation, pp 2519\u20132524 . https:\/\/doi.org\/10.1109\/ICRA46639.2022.9812125","DOI":"10.1109\/ICRA46639.2022.9812125"},{"key":"1176_CR20","doi-asserted-by":"publisher","unstructured":"Mottaghi R, Schenck C, Fox D, Farhadi A (2017) See the glass half full: Reasoning about liquid containers, their volume and content, pp 1889\u20131898. https:\/\/doi.org\/10.1109\/ICCV.2017.207","DOI":"10.1109\/ICCV.2017.207"},{"key":"1176_CR21","doi-asserted-by":"publisher","unstructured":"Piacenza P, Lee D, Isler V (2022) Pouring by feel: An analysis of tactile and proprioceptive sensing for accurate pouring. In: Proc. of Int. Conf. on Robotics and Automation, pp. 10248\u201310254. https:\/\/doi.org\/10.1109\/ICRA46639.2022.9811898","DOI":"10.1109\/ICRA46639.2022.9811898"},{"key":"1176_CR22","unstructured":"Xompero A, Sanchez-Matilla RMR, Cavallaro A Corsmal containers manipulation. Queen Mary University of London. https:\/\/doi.org\/10.17636\/101CORSMAL1"},{"issue":"12","key":"1176_CR23","doi-asserted-by":"publisher","first-page":"2762","DOI":"10.3390\/s17122762","volume":"17","author":"W Yuan","year":"2017","unstructured":"Yuan W, Dong S, Adelson EH (2017) Gelsight: high-resolution robot tactile sensors for estimating geometry and force. Sensors 17(12):2762","journal-title":"Sensors"},{"key":"1176_CR24","doi-asserted-by":"publisher","unstructured":"Nied\u017awiecki M, Cio\u0142ek M (2019) Fully adaptive savitzky-golay type smoothers. In: Proceedings of European Signal Processing Conference, pp 1\u20135. https:\/\/doi.org\/10.23919\/EUSIPCO.2019.8902652","DOI":"10.23919\/EUSIPCO.2019.8902652"},{"key":"1176_CR25","unstructured":"Logan B (2000) Mel frequency cepstral coefficients for music modeling. Society for Music Information Retrieval, Proc of Int"},{"key":"1176_CR26","doi-asserted-by":"crossref","unstructured":"Ishikawa R, Nagao Y, Hachiuma R, Saito H (2021) Audio-visual hybrid approach for filling mass estimation. In: International Conference on Pattern Recognition. Berlin, Heidelberg, pp 437\u2013450","DOI":"10.1007\/978-3-030-68793-9_32"},{"key":"1176_CR27","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","volume":"28","author":"Q Kong","year":"2020","unstructured":"Kong Q, Cao Y, Iqbal T, Wang Y, Wang W, Plumbley MD (2020) PANNs: large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Trans Audio, Speech, Language Process 28:2880\u20132894. https:\/\/doi.org\/10.1109\/TASLP.2020.3030497","journal-title":"IEEE\/ACM Trans Audio, Speech, Language Process"},{"key":"1176_CR28","doi-asserted-by":"publisher","unstructured":"Saito N, Dai NB, Ogata T, Mori H, Sugano S (2019) Real-time liquid pouring motion generation: End-to-end sensorimotor coordination for unknown liquid dynamics trained with deep neural networks. In: IEEE International Conference on Robotics and Biomimetics, pp 1077\u20131082 . https:\/\/doi.org\/10.1109\/ROBIO49542.2019.8961718","DOI":"10.1109\/ROBIO49542.2019.8961718"},{"key":"1176_CR29","doi-asserted-by":"publisher","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) MobileNetV2: Inverted residuals and linear bottlenecks. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, pp 4510\u20134520. https:\/\/doi.org\/10.1109\/CVPR.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1176_CR30","doi-asserted-by":"publisher","unstructured":"Hou Q, Zhou D, Feng J (2021) Coordinate attention for efficient mobile network design. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, pp 13708\u201313717 . https:\/\/doi.org\/10.1109\/CVPR46437.2021.01350","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"1176_CR31","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556"}],"container-title":["International Journal of Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12369-024-01176-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12369-024-01176-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12369-024-01176-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T14:55:03Z","timestamp":1761663303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12369-024-01176-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,15]]},"references-count":31,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1176"],"URL":"https:\/\/doi.org\/10.1007\/s12369-024-01176-4","relation":{},"ISSN":["1875-4791","1875-4805"],"issn-type":[{"type":"print","value":"1875-4791"},{"type":"electronic","value":"1875-4805"}],"subject":[],"published":{"date-parts":[[2024,10,15]]},"assertion":[{"value":"29 July 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}