{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:07:45Z","timestamp":1778080065379,"version":"3.51.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802256","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7492-7498","source":"Crossref","is-referenced-by-count":4,"title":["Language-driven Grasp Detection with Mask-guided Attention"],"prefix":"10.1109","author":[{"given":"Tuan","family":"Van Vo","sequence":"first","affiliation":[{"name":"FPT Software AI Center,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh Nhat","family":"Vu","sequence":"additional","affiliation":[{"name":"TU Wien,Automation & Control Institute,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoru","family":"Huang","sequence":"additional","affiliation":[{"name":"Imperial College,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An","family":"Vuong","sequence":"additional","affiliation":[{"name":"FPT Software AI Center,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[{"name":"University of Arkansas,Department of Computer Science & Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thieu","family":"Vo","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3129134"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2023.3328964"},{"key":"ref3","article-title":"Cliport: What and where pathways for robotic manipulation","author":"Shridhar","year":"2022","journal-title":"CoRL"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509439"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907124"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759156"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2011.5980145"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611277"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062122-025215"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610247"},{"key":"ref16","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref17","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","author":"Mu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref19","article-title":"Introducing ChatGPT","journal-title":"Software"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00648"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9402-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342331"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72655-2_21","article-title":"Language-driven 6-dof grasp detection using negative prompt guidance","volume-title":"ECCV","author":"Nguyen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811367"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01695"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/IROS58592.2024.10802007","article-title":"Lightweight language-driven grasp detection using conditional consistency model","volume-title":"IROS","author":"Nguyen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812360"},{"key":"ref36","article-title":"Language-guided robot grasping: Clip-based referring grasp synthesis in clutter","author":"Tziafas","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561994"},{"key":"ref38","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref41","article-title":"Learning video representations using contrastive bidirectional transformer","author":"Sun","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref43","article-title":"Univilm: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref44","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref45","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020"},{"key":"ref46","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"Zheng","year":"2020"},{"key":"ref47","article-title":"Point transformer","author":"Zhao","year":"2020"},{"key":"ref48","article-title":"Is space-time attention all you need for video understanding?","author":"Bertasius","year":"2021"},{"key":"ref49","article-title":"An image is worth 16x16 words, what is a video worth?","author":"Sharir","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852777"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967869"},{"key":"ref53","article-title":"Learning rgb-d feature embeddings for unseen object instance segmentation","author":"Xiang","year":"2021","journal-title":"CoRL"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811646"},{"key":"ref55","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref57","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017"},{"key":"ref58","article-title":"Learning two-branch neural networks for image-text matching tasks","author":"Wang","year":"2018","journal-title":"IEEE TPAMI"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref64","article-title":"Visualizing data using t-sne","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1582"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2023.102970"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802256.pdf?arnumber=10802256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:18Z","timestamp":1735196418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802256","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}