{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T13:39:37Z","timestamp":1774013977664,"version":"3.50.1"},"reference-count":58,"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","award":["62401196"],"award-info":[{"award-number":["62401196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241508"],"award-info":[{"award-number":["BK20241508"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3210801"],"award-info":[{"award-number":["2024YFC3210801"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.eswa.2025.130892","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T13:09:57Z","timestamp":1767013797000},"page":"130892","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["CLIP-driven feature disambiguation and cross-modal synergy for few-shot semantic segmentation"],"prefix":"10.1016","volume":"306","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9887-8851","authenticated-orcid":false,"given":"Shangjing","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2175-9943","authenticated-orcid":false,"given":"Feng","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1862-2070","authenticated-orcid":false,"given":"Xin","family":"Lyu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0251-553X","authenticated-orcid":false,"given":"Dafa","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0576-3181","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2025.130892_bib0001","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9465","article-title":"Meta-learning with task-adaptive loss function for few-shot learning","author":"Baik","year":"2021"},{"key":"10.1016\/j.eswa.2025.130892_bib0002","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"765","article-title":"Relevant intrinsic feature enhancement network for few-shot semantic segmentation","volume":"38","author":"Bao","year":"2024"},{"key":"10.1016\/j.eswa.2025.130892_bib0003","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"978","article-title":"Pixel matching network for cross-domain few-shot segmentation","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2025.130892_bib0004","series-title":"International conference on artificial neural networks","first-page":"243","article-title":"Multi-level metric learning for few-shot image recognition","author":"Chen","year":"2022"},{"key":"10.1016\/j.eswa.2025.130892_bib0005","doi-asserted-by":"crossref","first-page":"4361","DOI":"10.1109\/TMM.2022.3174405","article-title":"ApaNet: Adaptive prototypes alignment network for few-shot semantic segmentation","volume":"25","author":"Chen","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2025.130892_bib0006","doi-asserted-by":"crossref","first-page":"7197","DOI":"10.1109\/TMM.2024.3361181","article-title":"Visual and textual prior guided mask assemble for few-shot segmentation and beyond","volume":"26","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2025.130892_bib0007","doi-asserted-by":"crossref","first-page":"1432","DOI":"10.1109\/TIP.2024.3364056","article-title":"Dual branch multi-level semantic learning for few-shot segmentation","volume":"33","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2025.130892_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8680","article-title":"Image deformation meta-networks for one-shot learning","author":"Chen","year":"2019"},{"key":"10.1016\/j.eswa.2025.130892_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15434","article-title":"Weakly-supervised domain adaptive semantic segmentation with prototypical contrastive learning","author":"Das","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0010","doi-asserted-by":"crossref","first-page":"4654","DOI":"10.1109\/TIP.2024.3444190","article-title":"Pixel-level domain adaptation: A new perspective for enhancing weakly supervised semantic segmentation","volume":"33","author":"Du","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2025.130892_bib0011","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":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2025.130892_bib0012","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.eswa.2025.130892_bib0013","series-title":"European conference on computer vision","first-page":"108","article-title":"Cost aggregation with 4D convolutional swin transformer for few-shot segmentation","author":"Hong","year":"2022"},{"key":"10.1016\/j.eswa.2025.130892_bib0014","article-title":"FBINet: Few-shot semantic segmentation with foreground and background iteration","volume":"74","author":"Huang","year":"2025","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2025.130892_bib0015","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"603","article-title":"CCNet: Criss-cross attention for semantic segmentation","author":"Huang","year":"2019"},{"key":"10.1016\/j.eswa.2025.130892_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11719","article-title":"Task agnostic meta-learning for few-shot learning","author":"Jamal","year":"2019"},{"key":"10.1016\/j.eswa.2025.130892_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19606","article-title":"WinCLIP: Zero-\/few-shot anomaly classification and segmentation","author":"Jeong","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9979","article-title":"Integrative few-shot learning for classification and segmentation","author":"Kang","year":"2022"},{"issue":"1","key":"10.1016\/j.eswa.2025.130892_bib0019","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s11263-023-01886-8","article-title":"Few-shot segmentation via divide-and-conquer proxies","volume":"132","author":"Lang","year":"2024","journal-title":"International Journal of Computer Vision"},{"issue":"9","key":"10.1016\/j.eswa.2025.130892_bib0020","doi-asserted-by":"crossref","first-page":"10669","DOI":"10.1109\/TPAMI.2023.3265865","article-title":"Base and meta: A new perspective on few-shot segmentation","volume":"45","author":"Lang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2025.130892_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8334","article-title":"Adaptive prototype learning and allocation for few-shot segmentation","author":"Li","year":"2021"},{"key":"10.1016\/j.eswa.2025.130892_bib0022","doi-asserted-by":"crossref","first-page":"2596","DOI":"10.1109\/TITS.2024.3496538","article-title":"Class-balanced sampling and discriminative stylization for domain generalization semantic segmentation","volume":"26","author":"Liao","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2025.130892_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122173","article-title":"SSL-ProtoNet: Self-supervised learning prototypical networks for few-shot learning","volume":"238","author":"Lim","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2025.130892_bib0024","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1925","article-title":"RefineNet: Multi-path refinement networks for high-resolution semantic segmentation","author":"Lin","year":"2017"},{"key":"10.1016\/j.eswa.2025.130892_bib0025","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2025.130892_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15305","article-title":"CLIP is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation","author":"Lin","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0027","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4165","article-title":"CRNet: Cross-reference networks for few-shot segmentation","author":"Liu","year":"2020"},{"key":"10.1016\/j.eswa.2025.130892_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11573","article-title":"Learning non-target knowledge for few-shot semantic segmentation","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2025.130892_bib0029","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"10.1016\/j.eswa.2025.130892_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7086","article-title":"Image segmentation using text and image prompts","author":"L\u00fcddecke","year":"2022"},{"key":"10.1016\/j.eswa.2025.130892_bib0031","series-title":"International conference on machine learning","first-page":"23033","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","author":"Luo","year":"2023"},{"issue":"2","key":"10.1016\/j.eswa.2025.130892_bib0032","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1109\/TPAMI.2023.3329725","article-title":"PFENet++: Boosting few-shot semantic segmentation with the noise-filtered context-aware prior mask","volume":"46","author":"Luo","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2025.130892_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125377","article-title":"Combining hierarchical sparse representation with adaptive prompt for few-shot segmentation","volume":"260","author":"Luo","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2025.130892_bib0034","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6941","article-title":"Hypercorrelation squeeze for few-shot segmentation","author":"Min","year":"2021"},{"key":"10.1016\/j.eswa.2025.130892_bib0035","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"622","article-title":"Feature weighting and boosting for few-shot segmentation","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.eswa.2025.130892_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23641","article-title":"Hierarchical dense correlation distillation for few-shot segmentation","author":"Peng","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0037","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.eswa.2025.130892_bib0038","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., & Boots, B. (2017). One-shot learning for semantic segmentation. arXiv: 1709.03410.","DOI":"10.5244\/C.31.167"},{"key":"10.1016\/j.eswa.2025.130892_bib0039","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4784","article-title":"CGMGM: A cross-gaussian mixture generative model for few-shot semantic segmentation","volume":"38","author":"Shen","year":"2024"},{"key":"10.1016\/j.eswa.2025.130892_bib0040","series-title":"European conference on computer vision","first-page":"151","article-title":"Dense cross-query-and-support attention weighted mask aggregation for few-shot segmentation","author":"Shi","year":"2022"},{"issue":"2","key":"10.1016\/j.eswa.2025.130892_bib0041","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","article-title":"Prior guided feature enrichment network for few-shot segmentation","volume":"44","author":"Tian","year":"2020","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10.1016\/j.eswa.2025.130892_bib0042","first-page":"3637","article-title":"Matching networks for one shot learning","volume":"29","author":"Vinyals","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2025.130892_bib0043","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, L., Zhang, W., Zhang, J., Gan, Z., Wang, Y., Wang, C., & Wang, H. (2023a). Iterative few-shot semantic segmentation from image label text. arXiv: 2303.05646.","DOI":"10.24963\/ijcai.2022\/193"},{"key":"10.1016\/j.eswa.2025.130892_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3941","article-title":"Rethinking prior information generation with clip for few-shot segmentation","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2025.130892_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7183","article-title":"Rethinking the correlation in few-shot segmentation: A buoys view","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0046","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11686","article-title":"CRIS: CLIP-driven referring image segmentation","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2025.130892_bib0047","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"517","article-title":"Learning meta-class memory for few-shot semantic segmentation","author":"Wu","year":"2021"},{"key":"10.1016\/j.eswa.2025.130892_bib0048","series-title":"European conference on computer vision","first-page":"416","article-title":"Eliminating feature ambiguity for few-shot segmentation","author":"Xu","year":"2024"},{"key":"10.1016\/j.eswa.2025.130892_bib0049","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"655","article-title":"Self-calibrated cross attention network for few-shot segmentation","author":"Xu","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7071","article-title":"A simple framework for text-supervised semantic segmentation","author":"Yi","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0051","doi-asserted-by":"crossref","first-page":"4198","DOI":"10.1109\/TPAMI.2025.3543191","article-title":"Frozen CLIP-DINO: A strong backbone for weakly supervised semantic segmentation","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2025.130892_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5217","article-title":"CANet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning","author":"Zhang","year":"2019"},{"key":"10.1016\/j.eswa.2025.130892_bib0053","doi-asserted-by":"crossref","first-page":"6655","DOI":"10.1109\/TNNLS.2024.3400592","article-title":"Few-shot learning with enhancements to data augmentation and feature extraction","volume":"36","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2025.130892_bib0054","doi-asserted-by":"crossref","first-page":"5031","DOI":"10.1109\/TIP.2023.3287506","article-title":"Learning shape-invariant representation for generalizable semantic segmentation","volume":"32","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"10.1016\/j.eswa.2025.130892_bib0055","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/TCSVT.2023.3285091","article-title":"Fine-grained self-supervision for generalizable semantic segmentation","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2025.130892_bib0056","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125552","article-title":"On filling the intra-class and inter-class gaps for few-shot segmentation","volume":"261","author":"Zhang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2025.130892_bib0057","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11175","article-title":"ZegCLIP: Towards adapting clip for zero-shot semantic segmentation","author":"Zhou","year":"2023"},{"key":"10.1016\/j.eswa.2025.130892_bib0058","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3370","article-title":"Addressing background context bias in few-shot segmentation through iterative modulation","author":"Zhu","year":"2024"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417425045075?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417425045075?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T11:03:03Z","timestamp":1774004583000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417425045075"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":58,"alternative-id":["S0957417425045075"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2025.130892","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CLIP-driven feature disambiguation and cross-modal synergy for few-shot semantic segmentation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2025.130892","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"130892"}}