{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T18:44:34Z","timestamp":1761677074782},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747110","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"9142-9146","source":"Crossref","is-referenced-by-count":5,"title":["Shared Transformer Encoder with Mask-Based 3d Model Estimation for Container Mass Estimation"],"prefix":"10.1109","author":[{"given":"Tomoya","family":"Matsubara","sequence":"first","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seitaro","family":"Otsuki","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuiga","family":"Wada","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haruka","family":"Matsuo","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takumi","family":"Komatsu","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yui","family":"Iioka","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hideo","family":"Saito","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506112"},{"key":"ref11","first-page":"210","article-title":"Accurate pouring with an autonomous robot using an rgb-d camera","author":"do","year":"2018","journal-title":"International Conference on Intelligent Autonomous Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968303"},{"key":"ref13","first-page":"437","article-title":"Audio-visual hybrid approach for filling mass estimation","author":"ishikawa","year":"2021","journal-title":"International Conference on Pattern Recognition"},{"key":"ref14","first-page":"423","article-title":"Top-1 corsmal challenge 2020 submission: Filling mass estimation using multi-modal observations of humanrobot handovers","author":"iashin","year":"2021","journal-title":"International Conference on Pattern Recognition"},{"journal-title":"Python Reference Manual","year":"1995","author":"van rossum","key":"ref15"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref16"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref19","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ARSO46408.2019.8948750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026970"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"article-title":"Reactive human-to-robot handovers of arbitrary objects","year":"2020","author":"yang","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087172"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969200"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075365"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.207"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054112"},{"article-title":"Corsmal containers manipulation (1.0) [data set]","year":"2021","author":"xompero","key":"ref21"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747110.pdf?arnumber=9747110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:28Z","timestamp":1661199208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747110","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}