{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T07:44:43Z","timestamp":1777880683748,"version":"3.51.4"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.knosys.2026.115590","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:11:18Z","timestamp":1772093478000},"page":"115590","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Interactive image segmentation based on semantic collaboration of cross-modal prior information"],"prefix":"10.1016","volume":"339","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-2089","authenticated-orcid":false,"given":"Boyu","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7308-5453","authenticated-orcid":false,"given":"Zongyuan","family":"Ding","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1236-6141","authenticated-orcid":false,"given":"Hongyuan","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1738-1095","authenticated-orcid":false,"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4324-5431","authenticated-orcid":false,"given":"Dike","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3073-3763","authenticated-orcid":false,"given":"Jiaying","family":"Tang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115590_bib0001","series-title":"European Conference on Computer Vision","first-page":"701","article-title":"Self-support few-shot semantic segmentation","author":"Fan","year":"2022"},{"key":"10.1016\/j.knosys.2026.115590_bib0002","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18392","article-title":"Instructpix2pix: learning to follow image editing instructions","author":"Brooks","year":"2023"},{"issue":"12","key":"10.1016\/j.knosys.2026.115590_bib0003","doi-asserted-by":"crossref","first-page":"10998","DOI":"10.1109\/TPAMI.2024.3452629","article-title":"Deep interactive segmentation of medical images: a systematic review and taxonomy","volume":"46","author":"Marinov","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115590_bib0004","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22290","article-title":"Simpleclick: interactive image segmentation with simple vision transformers","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.115590_bib0005","first-page":"1","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":": Int. Conf. Learn. Represent."},{"key":"10.1016\/j.knosys.2026.115590_bib0006","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5017","article-title":"Cfr-icl: cascade-forward refinement with iterative click loss for interactive image segmentation","volume":"38","author":"Sun","year":"2024"},{"key":"10.1016\/j.knosys.2026.115590_bib0007","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"issue":"2","key":"10.1016\/j.knosys.2026.115590_bib0008","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1038\/35039043","article-title":"Visual attention: insights from brain imaging","volume":"1","author":"Kanwisher","year":"2000","journal-title":"Nat. Rev. Neurosci."},{"issue":"2","key":"10.1016\/j.knosys.2026.115590_bib0009","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-Inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"issue":"1","key":"10.1016\/j.knosys.2026.115590_bib0010","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/TPAMI.2024.3461779","article-title":"Prompt-and-transfer: dynamic class-aware enhancement for few-shot segmentation","volume":"47","author":"Bi","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115590_bib0011","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.knosys.2026.115590_bib0012","series-title":"Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001","first-page":"105","article-title":"Interactive graph cuts for optimal boundary & region segmentation of objects in ND images","volume":"1","author":"Boykov","year":"2001"},{"issue":"3","key":"10.1016\/j.knosys.2026.115590_bib0013","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1145\/1015706.1015720","article-title":"\u201d Grabcut\u201d interactive foreground extraction using iterated graph cuts","volume":"23","author":"Rother","year":"2004","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"11","key":"10.1016\/j.knosys.2026.115590_bib0014","doi-asserted-by":"crossref","first-page":"1768","DOI":"10.1109\/TPAMI.2006.233","article-title":"Random walks for image segmentation","volume":"28","author":"Grady","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115590_bib0015","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"373","article-title":"Deep interactive object selection","author":"Xu","year":"2016"},{"key":"10.1016\/j.knosys.2026.115590_bib0016","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.neunet.2018.10.009","article-title":"A fully convolutional two-stream fusion network for interactive image segmentation","volume":"109","author":"Hu","year":"2019","journal-title":"Neural Netw."},{"key":"10.1016\/j.knosys.2026.115590_bib0017","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"2746","article-title":"Regional interactive image segmentation networks","author":"Liew","year":"2017"},{"key":"10.1016\/j.knosys.2026.115590_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11602","article-title":"Content-aware multi-level guidance for interactive instance segmentation","author":"Majumder","year":"2019"},{"key":"10.1016\/j.knosys.2026.115590_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5297","article-title":"Interactive image segmentation via backpropagating refinement scheme","author":"Jang","year":"2019"},{"key":"10.1016\/j.knosys.2026.115590_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8623","article-title":"F-brs: rethinking backpropagating refinement for interactive segmentation","author":"Sofiiuk","year":"2020"},{"key":"10.1016\/j.knosys.2026.115590_bib0021","series-title":"European Conference on Computer Vision","first-page":"417","article-title":"Phraseclick: toward achieving flexible interactive segmentation by phrase and click","author":"Ding","year":"2020"},{"issue":"8","key":"10.1016\/j.knosys.2026.115590_bib0022","first-page":"1705","article-title":"Deep interactive image segmentation based on fusion multi-scale annotation information","volume":"58","author":"Zongyuan","year":"2021","journal-title":"J. Comput. Res. Dev"},{"key":"10.1016\/j.knosys.2026.115590_bib0023","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"28264","article-title":"GoodSAM: bridging domain and capacity gaps via segment anything model for distortion-aware panoramic semantic segmentation","author":"Zhang","year":"2024"},{"issue":"3","key":"10.1016\/j.knosys.2026.115590_bib0024","doi-asserted-by":"crossref","first-page":"5759","DOI":"10.1109\/TNNLS.2024.3378295","article-title":"Adaptiveclick: click-aware transformer with adaptive focal loss for interactive image segmentation","volume":"36","author":"Lin","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.knosys.2026.115590_bib0025","doi-asserted-by":"crossref","first-page":"2951","DOI":"10.1109\/TCSVT.2024.3378000","article-title":"Clickadapter: integrating details into interactive segmentation model with adapter","volume":"35","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.115590_bib0026","series-title":"European Conference on Computer Vision","first-page":"93","article-title":"Click prompt learning with optimal transport for interactive segmentation","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.115590_bib0027","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4051","article-title":"Mfp: making full use of probability maps for interactive image segmentation","author":"Lee","year":"2024"},{"issue":"000","key":"10.1016\/j.knosys.2026.115590_bib0028","first-page":"14","article-title":"Click-Pixel cognition fusion network with balanced cut for interactive image segmentation","volume":"33","author":"Lin","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.115590_bib0029","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1698","article-title":"Variance-insensitive and target-preserving mask refinement for interactive image segmentation","volume":"38","author":"Fang","year":"2024"},{"key":"10.1016\/j.knosys.2026.115590_bib0030","article-title":"Diffclick: click-Differentiated enhancement network for interactive segmentation","author":"Song","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.115590_bib0031","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"19356","article-title":"SAM-REF: Introducing image-Prompt synergy during interaction for detail enhancement in the segment anything model","author":"Yu","year":"2025"},{"key":"10.1016\/j.knosys.2026.115590_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3625","article-title":"ROS-SAM: High-Quality interactive segmentation for remote sensing moving object","author":"Shan","year":"2025"},{"issue":"2","key":"10.1016\/j.knosys.2026.115590_bib0033","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1016\/j.patcog.2009.03.008","article-title":"A comparative evaluation of interactive segmentation algorithms","volume":"43","author":"McGuinness","year":"2010","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.115590_bib0034","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"724","article-title":"A benchmark dataset and evaluation methodology for video object segmentation","author":"Perazzi","year":"2016"},{"issue":"2","key":"10.1016\/j.knosys.2026.115590_bib0035","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.115590_bib0036","series-title":"2011 International Conference on Computer Vision","first-page":"991","article-title":"Semantic contours from inverse detectors","author":"Hariharan","year":"2011"},{"key":"10.1016\/j.knosys.2026.115590_bib0037","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.knosys.2026.115590_bib0038","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5356","article-title":"Lvis: a dataset for large vocabulary instance segmentation","author":"Gupta","year":"2019"},{"key":"10.1016\/j.knosys.2026.115590_bib0039","article-title":"Segmented anisotropic ssTEM dataset of neural tissue","author":"Gerhard","year":"2013","journal-title":"figshare"},{"key":"10.1016\/j.knosys.2026.115590_bib0040","unstructured":"U. Baid, S. Ghodasara, S. Mohan, M. Bilello, E. Calabrese, E. Colak, K. Farahani, J. Kalpathy-Cramer, F.C. Kitamura, S. Pati, et al., The rsna-asnr-miccai brats 2021 benchmark on brain tumor segmentation and radiogenomic classification, (2021). arXiv preprint arXiv: 2107.02314."},{"key":"10.1016\/j.knosys.2026.115590_bib0041","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.media.2018.11.009","article-title":"Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: data from the osteoarthritis initiative","volume":"52","author":"Ambellan","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.knosys.2026.115590_bib0042","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2637","article-title":"Focuscut: diving into a focus view in interactive segmentation","author":"Lin","year":"2022"},{"key":"10.1016\/j.knosys.2026.115590_bib0043","first-page":"577","article-title":"Interactive image segmentation with latent diversity","author":"Li","year":"2018","journal-title":"IEEE"},{"key":"10.1016\/j.knosys.2026.115590_bib0044","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"7345","article-title":"Conditional diffusion for interactive segmentation","author":"Chen","year":"2021"},{"key":"10.1016\/j.knosys.2026.115590_bib0045","series-title":"2022 IEEE International Conference on Image Processing (ICIP)","first-page":"3141","article-title":"Reviving iterative training with mask guidance for interactive segmentation","author":"Sofiiuk","year":"2022"},{"key":"10.1016\/j.knosys.2026.115590_bib0046","series-title":"European Conference on Computer Vision","first-page":"728","article-title":"Pseudoclick: interactive image segmentation with click imitation","author":"Liu","year":"2022"},{"key":"10.1016\/j.knosys.2026.115590_bib0047","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1300","article-title":"Focalclick: towards practical interactive image segmentation","author":"Chen","year":"2022"},{"key":"10.1016\/j.knosys.2026.115590_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19488","article-title":"Interactive segmentation as gaussion process classification","author":"Zhou","year":"2023"},{"key":"10.1016\/j.knosys.2026.115590_bib0049","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22773","article-title":"Efficient mask correction for click-based interactive image segmentation","author":"Du","year":"2023"},{"key":"10.1016\/j.knosys.2026.115590_bib0050","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22301","article-title":"Interformer: real-time interactive image segmentation","author":"Huang","year":"2023"},{"key":"10.1016\/j.knosys.2026.115590_bib0051","unstructured":"K. Li, H. Cheng, G. Vosselman, M.Y. Yang, Learning from Exemplars for Interactive Image Segmentation,(2024). arXiv preprint arXiv: 2406.11472."},{"key":"10.1016\/j.knosys.2026.115590_bib0052","doi-asserted-by":"crossref","DOI":"10.1109\/TIP.2024.3492713","article-title":"PVPUFormer: Probabilistic visual prompt unified transformer for interactive image segmentation","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Image Process."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126003308?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126003308?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:19:05Z","timestamp":1777594745000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126003308"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":52,"alternative-id":["S0950705126003308"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115590","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Interactive image segmentation based on semantic collaboration of cross-modal prior information","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115590","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115590"}}