{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:13:17Z","timestamp":1780762397350,"version":"3.54.1"},"reference-count":63,"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\/iros58592.2024.10801872","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"14196-14203","source":"Crossref","is-referenced-by-count":25,"title":["Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning"],"prefix":"10.1109","author":[{"given":"Shaohua","family":"Dong","sequence":"first","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhe","family":"Feng","sequence":"additional","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Yang","sequence":"additional","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongfang","family":"Liu","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology,Dept. of Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Fan","sequence":"additional","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"NeurIPS","author":"Xie"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2775628"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref5","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"NeurIPS","author":"Cheng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3306368"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3109518"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3164899"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref21","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume-title":"NeurIPS","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01604"},{"key":"ref23","article-title":"Prompt-matched semantic segmentation","author":"Liu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref33","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01900"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref36","article-title":"Pgdenet: Progressive guided fusion and depth enhancement network for rgb-d indoor scene parsing","author":"Zhou","year":"2022","journal-title":"IEEE TMM"},{"key":"ref37","article-title":"Dformer: Rethinking rgbd representation learning for semantic segmentation","author":"Yin","year":"2023"},{"key":"ref38","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"issue":"3","key":"ref39","first-page":"1000","article-title":"Fuseseg: Semantic segmentation of urban scenes based on rgb and thermal data fusion","volume":"18","author":"Sun","year":"2020","journal-title":"IEEE TASE"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3219350"},{"key":"ref41","article-title":"Cacfnet: Cross-modal attention cascaded fusion network for rgb-t urban scene parsing","author":"Zhou","year":"2023","journal-title":"IEEE TIV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2632856.2632866"},{"issue":"5","key":"ref45","first-page":"2075","article-title":"Rethinking rgb-d salient object detection: Models, data sets, and large-scale benchmarks","volume":"32","author":"Fan","year":"2020","journal-title":"IEEE TNNLS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.359"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_39"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_14"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00353"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_17"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242775"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1702-6_36"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3171688"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00404"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01377"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2959253"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636192"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00112"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247743"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.39"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/97"}],"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\/10801872.pdf?arnumber=10801872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:58:44Z","timestamp":1735196324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801872","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}