{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:56:28Z","timestamp":1771955788940,"version":"3.50.1"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611354","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"3288-3295","source":"Crossref","is-referenced-by-count":3,"title":["Towards Unified Interactive Visual Grounding in The Wild"],"prefix":"10.1109","author":[{"given":"Jie","family":"Xu","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyi","family":"Si","sequence":"additional","affiliation":[{"name":"ByteDance Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuguang","family":"Lan","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Kong","sequence":"additional","affiliation":[{"name":"ByteDance Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919897133"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812360"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref9","article-title":"Invig: Benchmarking interactive visual grounding with 500k human-robot interactions","author":"Zhang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5898\/JHRI.2.2.Deits"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1121241.1121290"},{"key":"ref13","first-page":"915","article-title":"An effective personal mobile robot agent through symbiotic human-robot interaction","volume":"10","author":"Rosenthal","year":"2010","journal-title":"AAMAS"},{"key":"ref14","article-title":"Asking for help using inverse semantics","author":"Tellex","year":"2014","journal-title":"Robotics: Science and Systems Foundation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161333"},{"key":"ref19","article-title":"Devi Parikh, and Dhruv Batra","author":"Das","year":"2017","journal-title":"Visual dialog"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref21","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019"},{"key":"ref22","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","volume-title":"International Conference on Learning Representations","author":"Su"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref26","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"International Conference on Machine Learning","author":"Cho"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","article-title":"Flamingo: a visual language model for fewshot learning","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proceedings of the 39th international conference on Machine learning","author":"Zeng"},{"key":"ref30","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequenceto-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref31","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref33","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref34","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref35","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref36","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref38","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref39","article-title":"Llama 2: Open foundation and finetuned chat models","author":"Touvron","year":"2023"},{"key":"ref40","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Scao","year":"2022"},{"key":"ref41","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref42","article-title":"What matters in training a gpt4-style language model with multimodal inputs?","author":"Zeng","year":"2023"},{"key":"ref43","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref44","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref45","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref46","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"issue":"1","key":"ref47","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref48","article-title":"Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019"},{"key":"ref49","first-page":"24","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref50","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref51","article-title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification","author":"Krasin","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00557"},{"key":"ref53","article-title":"End-to-end optimization of goaldriven and visually grounded dialogue systems","author":"Strub","year":"2017"},{"key":"ref54","article-title":"Visual dialogue state tracking for question generation","author":"Pang","year":"2019"},{"key":"ref55","article-title":"Beyond task success: A closer look at jointly learning to see, ask, and guesswhat","author":"Shekhar","year":"2018"},{"key":"ref56","first-page":"1","article-title":"Improving goal-oriented visual dialog agents via advanced recurrent nets with tempered policy gradient","author":"Zhao","year":"2018","journal-title":"LaCATODA@ IJCAI"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_40"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref59","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"Zeng","year":"2021"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611354.pdf?arnumber=10611354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:16:56Z","timestamp":1723349816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611354","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}