{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:54:59Z","timestamp":1780764899935,"version":"3.54.1"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tcsvt.2025.3536086","type":"journal-article","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T19:12:31Z","timestamp":1738177951000},"page":"5858-5871","source":"Crossref","is-referenced-by-count":6,"title":["CPAL: Cross-Prompting Adapter With LoRAs for RGB+X Semantic Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2686-3002","authenticated-orcid":false,"given":"Ye","family":"Liu","sequence":"first","affiliation":[{"name":"School of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1125-9299","authenticated-orcid":false,"given":"Miaohui","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-4165","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing and Communications, Lancaster University, Lancaster, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015866"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICUFN.2018.8436956"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00101"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056726"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3187664"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382354"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.147"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.533"},{"key":"ref11","article-title":"RedNet: Residual encoder\u2013decoder network for indoor RGB-D semantic segmentation","author":"Jiang","year":"2018","journal-title":"arXiv:1806.01054"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106729"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272269"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01972"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00067"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3349072"},{"key":"ref20","article-title":"Variational probabilistic fusion network for RGB-T semantic segmentation","author":"Lin","year":"2023","journal-title":"arXiv:2307.08536"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.47"},{"key":"ref23","article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021","journal-title":"arXiv:2110.07602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27981"},{"key":"ref25","article-title":"Efficient multimodal semantic segmentation via dual-prompt learning","author":"Dong","year":"2023","journal-title":"arXiv:2312.00360"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref36","article-title":"CLUSTSEG: Clustering for universal segmentation","author":"Liang","year":"2023","journal-title":"arXiv:2305.02187"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3009373"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_20"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref42","article-title":"Sigma: Siamese mamba network for multi-modal semantic segmentation","author":"Wan","year":"2024","journal-title":"arXiv:2404.04256"},{"key":"ref43","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25160"},{"key":"ref45","first-page":"36889","article-title":"Polyhistor: Parameter-efficient multi-task adaptation for dense vision tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Liu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref47","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref48","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref49","first-page":"9853","article-title":"Sparse structure search for delta tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Hu"},{"key":"ref50","article-title":"Efficient NLP model finetuning via multistage data filtering","author":"Ouyang","year":"2022","journal-title":"arXiv:2207.14386"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.381"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"ref57","article-title":"DDD17: End-to-end Davis driving dataset","author":"Binas","year":"2017","journal-title":"arXiv:1711.01458"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612288"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296162"},{"key":"ref63","article-title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","author":"Yin","year":"2023","journal-title":"arXiv:2309.09668"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00127"},{"key":"ref65","article-title":"GeminiFusion: Efficient pixel-wise multimodal fusion for vision transformer","author":"Jia","year":"2024","journal-title":"arXiv:2406.01210"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_31"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/487"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208833"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216313"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229359"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281419"},{"key":"ref74","article-title":"HAPNet: Toward superior RGB-thermal scene parsing via hybrid, asymmetric, and progressive heterogeneous feature fusion","author":"Li","year":"2024","journal-title":"arXiv:2404.03527"},{"key":"ref75","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref78","article-title":"Is attention better than matrix decomposition?","author":"Geng","year":"2021","journal-title":"arXiv:2109.04553"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3437415"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ac9b86"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00586"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00112"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636192"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/2632856.2632866"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_39"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_14"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00353"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_17"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242775"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247743"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.39"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/97"},{"key":"ref102","article-title":"AdaMix: Mixture-of-adapter for parameter-efficient tuning of large language models","author":"Wang","year":"2022","journal-title":"arXiv:2205.12410"},{"key":"ref103","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021","journal-title":"arXiv:2110.04366"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11027896\/10857375.pdf?arnumber=10857375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T04:53:46Z","timestamp":1749531226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10857375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":104,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3536086","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}