{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:25:37Z","timestamp":1775579137099,"version":"3.50.1"},"reference-count":47,"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\/iros58592.2024.10801488","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"11610-11617","source":"Crossref","is-referenced-by-count":6,"title":["Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors"],"prefix":"10.1109","author":[{"given":"Nikolaos","family":"Tsagkas","sequence":"first","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Jack","family":"Rome","sequence":"additional","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Subramanian","family":"Ramamoorthy","sequence":"additional","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Oisin Mac","family":"Aodha","sequence":"additional","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Chris Xiaoxuan","family":"Lu","sequence":"additional","affiliation":[{"name":"University College London,Department of Computer Science,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611347"},{"key":"ref2","article-title":"D3 fields: Dynamic 3d descriptor fields for zero-shot generalizable robotic manipulation","author":"Wang","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241281508"},{"key":"ref4","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"CoRL","author":"Shen"},{"key":"ref5","article-title":"Vl-fields: Towards language-grounded neural implicit spatial representations","volume-title":"ICRA Workshops","author":"Tsagkas"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610243"},{"key":"ref9","article-title":"Kite: Keypoint-conditioned policies for semantic manipulation","author":"Sundaresan","year":"2023"},{"key":"ref10","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"CoRL","author":"Shridhar"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1055\/a-1858-6495"},{"key":"ref12","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref13","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Padalkar","year":"2023"},{"key":"ref14","article-title":"On bringing robots home","author":"Shafiullah","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref16","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref17","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"ICML","author":"Nichol"},{"key":"ref18","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref19","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NeurIPS","author":"Saharia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref21","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","volume-title":"ICLR","author":"Couairon"},{"key":"ref22","article-title":"A tale of two features: Stable diffusion complements dino for zero-shot semantic correspondence","volume-title":"NeurIPS","author":"Zhang"},{"key":"ref23","article-title":"Diffusion hyperfeatures: Searching through time and space for semantic correspondence","volume-title":"NeurIPS","author":"Luo"},{"key":"ref24","article-title":"Emergent correspondence from image diffusion","volume-title":"NeurIPS","author":"Tang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref26","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","volume-title":"CoRL","author":"Huang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197121"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561980"},{"key":"ref29","article-title":"Keypoints into the future: Self-supervised correspondence in model-based reinforcement learning","volume-title":"CoRL","author":"Manuelli"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref31","article-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation","volume-title":"CoRL","author":"Florence"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812291"},{"key":"ref33","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref35","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref39","article-title":"Text-to-image diffusion models are zero shot classifiers","volume-title":"NeurIPS","author":"Clark"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref41","article-title":"Slime: Segment like me","volume-title":"ICLR","author":"Khani"},{"key":"ref42","article-title":"Pair-diffusion: Object-level image editing with structure-and-appearance paired diffusion models","author":"Goel","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref45","article-title":"Unsupervised semantic correspondence using stable diffusion","volume-title":"NeurIPS","author":"Hedlin"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01846"}],"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\/10801488.pdf?arnumber=10801488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:57:28Z","timestamp":1735196248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801488","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}