{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:44:58Z","timestamp":1758980698842,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"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":[[2023,8,28]]},"DOI":"10.1109\/ro-man57019.2023.10309325","type":"proceedings-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:07:48Z","timestamp":1699884468000},"page":"2604-2609","source":"Crossref","is-referenced-by-count":2,"title":["CLIPGraphs: Multimodal Graph Networks to Infer Object-Room Affinities"],"prefix":"10.1109","author":[{"given":"Ayush","family":"Agrawal","sequence":"first","affiliation":[{"name":"IIIT,Robotics Research Center,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raghav","family":"Arora","sequence":"additional","affiliation":[{"name":"IIIT,Robotics Research Center,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahana","family":"Datta","sequence":"additional","affiliation":[{"name":"IIIT,Robotics Research Center,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Snehasis","family":"Banerjee","sequence":"additional","affiliation":[{"name":"IIIT,Robotics Research Center,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brojeshwar","family":"Bhowmick","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services,TCS Research,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna Murthy","family":"Jatavallabhula","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,CSAIL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohan","family":"Sridharan","sequence":"additional","affiliation":[{"name":"University of Birmingham,Intelligent Robotics Lab,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Madhava","family":"Krishna","sequence":"additional","affiliation":[{"name":"IIIT,Robotics Research Center,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Topological semantic graph memory for image-goal navigation","author":"kim","year":"2022","journal-title":"Conference on Robot Learning"},{"article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","year":"2021","author":"schuhmann","key":"ref35"},{"key":"ref12","article-title":"On evaluation of embodied navigation agents","volume":"abs 1807 6757","author":"anderson","year":"2018","journal-title":"ArXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref15","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","volume":"abs 2006 13171","author":"batra","year":"2020","journal-title":"ArXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS52745.2021.9650044"},{"key":"ref36","first-page":"1134","article-title":"Time-contrastive networks: Self-supervised learning from video","author":"sermanet","year":"2017","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"dosovitskiy","key":"ref31"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"wijmans","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref33","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref10","article-title":"Reproducible scaling laws for contrastive language-image learning","volume":"abs 2212 7143","author":"cherti","year":"2022","journal-title":"ArXiv"},{"article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","year":"2022","author":"schuhmann","key":"ref32"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_21"},{"article-title":"Rearrangement: A challenge for embodied ai","year":"2020","author":"batra","key":"ref1"},{"key":"ref17","first-page":"4089","article-title":"Iqa: Visual question answering in interactive environments","author":"gordon","year":"2017","journal-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref39","article-title":"Clip-fields: Weakly supervised semantic fields for robotic memory","volume":"abs 2210 5663","author":"shafiullah","year":"2022","journal-title":"ArXiv"},{"key":"ref16","first-page":"2135","article-title":"Embodied question answering","author":"das","year":"2017","journal-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"ref38","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume":"29","author":"sohn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"ref18","article-title":"Videonavqa: Bridging the gap between visual and embodied question answering","author":"cangea","year":"2019","journal-title":"British Machine Vision Conference"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"ref23","first-page":"3674","article-title":"Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments","author":"anderson","year":"2017","journal-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref25","first-page":"20","article-title":"The more you know: Using knowledge graphs for image classification","author":"marino","year":"2016","journal-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"article-title":"A simple approach for visual rearrangement: 3d mapping and semantic search","year":"2022","author":"trabucco","key":"ref20"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref22","article-title":"Teach: Task-driven embodied agents that chat","author":"padmakumar","year":"2021","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref21","first-page":"10 737","article-title":"Alfred: A benchmark for interpreting grounded instructions for everyday tasks","author":"shridhar","year":"2019","journal-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01443"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_28"},{"key":"ref29","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3233765"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160259"},{"key":"ref9","first-page":"1725","article-title":"Teaching agents how to map: Spatial reasoning for multi-object navigation","author":"marza","year":"2021","journal-title":"International Conference on Intelligent Robots and Systems"},{"key":"ref4","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume":"abs 2206 12403","author":"majumdar","year":"2022","journal-title":"ArXiv"},{"key":"ref3","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"abs 2007 643","author":"chaplot","year":"2020","journal-title":"ArXiv"},{"key":"ref6","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","volume":"abs 2203 10421","author":"gadre","year":"2022","journal-title":"ArXiv"},{"key":"ref5","first-page":"1092","article-title":"Object goal navigation using data regularized qlearning","author":"gireesh","year":"2022","journal-title":"International Conference on Automation Science and Engineering"},{"key":"ref40","article-title":"Roberta: A robustly optimized BERT pretraining approach","volume":"abs 1907 11692","author":"liu","year":"2019","journal-title":"CoRR"}],"event":{"name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2023,8,28]]},"location":"Busan, Korea, Republic of","end":{"date-parts":[[2023,8,31]]}},"container-title":["2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10309296\/10309265\/10309325.pdf?arnumber=10309325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T11:05:45Z","timestamp":1701255945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10309325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,28]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ro-man57019.2023.10309325","relation":{},"subject":[],"published":{"date-parts":[[2023,8,28]]}}}