{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T12:38:56Z","timestamp":1780576736117,"version":"3.54.1"},"reference-count":55,"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\/iros58592.2024.10802007","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"13719-13725","source":"Crossref","is-referenced-by-count":9,"title":["Lightweight Language-driven Grasp Detection using Conditional Consistency Model"],"prefix":"10.1109","author":[{"given":"Nghia","family":"Nguyen","sequence":"first","affiliation":[{"name":"FPT Software AI Center,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minh Nhat","family":"Vu","sequence":"additional","affiliation":[{"name":"TU Wien,Automation & Control Institute,Vienna,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoru","family":"Huang","sequence":"additional","affiliation":[{"name":"Imperial College,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"An","family":"Vuong","sequence":"additional","affiliation":[{"name":"FPT Software AI Center,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[{"name":"University of Arkansas,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thieu","family":"Vo","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636706"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811568"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref6","article-title":"Cliport: What and where pathways for robotic manipulation","author":"Shridhar","year":"2022","journal-title":"CoRL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852777"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191183"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561994"},{"key":"ref11","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Vuong","year":"2023","journal-title":"CoRL"},{"key":"ref12","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref13","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref14","article-title":"Language-guided robot grasping: Clip-based referring grasp synthesis in clutter","author":"Tziafas","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref16","article-title":"Learning 6-dof fine-grained grasp detection based on part affordance grounding","author":"Song","year":"2023"},{"key":"ref17","article-title":"Pave the way to grasp anything: Transferring foundation models for universal pick-place robots","author":"Yang","year":"2023"},{"key":"ref18","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Brohan","year":"2023","journal-title":"CoRL"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295255"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref21","article-title":"Towards scale balanced 6-dof grasp detection in cluttered scenes","author":"Ma","year":"2023","journal-title":"CoRL"},{"key":"ref22","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","author":"Shah","year":"2023","journal-title":"CoRL"},{"key":"ref23","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","author":"Ha","year":"2023","journal-title":"CoRL"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"ref26","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds","author":"Li","year":"2023"},{"key":"ref28","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref29","article-title":"Consistency models","author":"Song","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00798"},{"key":"ref31","article-title":"Light-grad: Lightweight diffusion probabilistic model for text-to-speech","author":"Chen","year":"2023","journal-title":"ICASSP"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.28"},{"key":"ref33","article-title":"Grasp-anything: Large-scale grasp dataset from foundation models","author":"Vuong","year":"2023","journal-title":"ICRA"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160842"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.22260\/ICRA2023","article-title":"Keypoint-graspnet: Keypoint-based 6-dof grasp generation from the monocular rgb-d input","author":"Chen","year":"2023","journal-title":"ICRA"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202237"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196740"},{"key":"ref39","article-title":"Language-driven 6-dof grasp detection using negative prompt guidance","author":"Nguyen","year":"2024","journal-title":"ECCV"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01695"},{"key":"ref41","article-title":"Language-driven grasp detection with mask-guided attention","author":"Vo","year":"2024","journal-title":"IROS"},{"key":"ref42","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref43","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3618356"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_18"},{"key":"ref47","article-title":"Language-driven scene synthesis using multi-conditional diffusion model","author":"Vuong","year":"2024","journal-title":"NeurIPS"},{"key":"ref48","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/4078.4079"},{"key":"ref51","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref52","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2023.102970"}],"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\/10802007.pdf?arnumber=10802007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:59:14Z","timestamp":1735196354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802007","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}