{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:28:06Z","timestamp":1793608086162,"version":"4.5.0"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004055","name":"King Fahd University of Petroleum & Minerals","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004055","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109721","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T16:03:07Z","timestamp":1791475387000},"page":"109721","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["SegVLM: Deformable attentive visual enhancement for referring image segmentation using vision-language model"],"prefix":"10.1016","volume":"206","author":[{"given":"Alaa","family":"Dalaq","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3693-4596","authenticated-orcid":false,"given":"Muzammil","family":"Behzad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.neunet.2026.109721_bib0001","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109721_bib0002","series-title":"Proceedings of the 37th international conference on machine learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"vol. 119","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109721_bib0003","series-title":"International conference on learning representations (ICLR)","article-title":"METRIS: Multi-expressions for transformer-based referring image segmentation","author":"Cho","year":"2025"},{"key":"10.1016\/j.neunet.2026.109721_bib0005","series-title":"Computer vision \u2013 ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, proceedings, Part XXVI","first-page":"290","article-title":"Fast-Moco: Boost momentum-based contrastive learning with combinatorial patches","author":"Ci","year":"2022"},{"key":"10.1016\/j.neunet.2026.109721_bib0006","series-title":"Proceedings of the IEEE international conference on computer vision (ICCV)","first-page":"764","article-title":"Deformable convolutional networks","author":"Dai","year":"2017"},{"key":"10.1016\/j.neunet.2026.109721_bib0007","series-title":"Advances in neural information processing systems (NeurIPS)","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"10.1016\/j.neunet.2026.109721_bib0008","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., & Jiang, X. (2021). Vision-language transformer and query generation for referring segmentation. arXiv preprint arXiv:2108.05565.","DOI":"10.1109\/ICCV48922.2021.01601"},{"issue":"2","key":"10.1016\/j.neunet.2026.109721_bib0009","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 (IJCV)"},{"key":"10.1016\/j.neunet.2026.109721_bib0010","series-title":"2006\u202fIEEE computer society conference on computer vision and pattern recognition (CVPR\u201906)","first-page":"1735","article-title":"Dimensionality reduction by learning an invariant mapping","volume":"vol. 2","author":"Hadsell","year":"2006"},{"issue":"3","key":"10.1016\/j.neunet.2026.109721_bib0011","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.32604\/cmc.2024.055478","article-title":"A real-time semantic segmentation method based on transformer for autonomous driving","volume":"81","author":"Hao","year":"2024","journal-title":"Computers, Materials & Continua"},{"key":"10.1016\/j.neunet.2026.109721_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.neunet.2026.109721_bib0013","series-title":"Proceedings of the IEEE international conference on computer vision (ICCV)","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017"},{"issue":"6","key":"10.1016\/j.neunet.2026.109721_bib0004","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MS.2019.2936273","article-title":"Howard Chu on lightning memory-mapped database","volume":"36","author":"Henry","year":"2019","journal-title":"IEEE Software"},{"issue":"8","key":"10.1016\/j.neunet.2026.109721_bib0014","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2026.109721_bib0015","series-title":"European conference on computer vision (ECCV)","first-page":"108","article-title":"Segmentation from natural language expressions","author":"Hu","year":"2016"},{"key":"10.1016\/j.neunet.2026.109721_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"4424","article-title":"Bi-directional relationship inferring network for referring image segmentation","author":"Hu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109721_bib0017","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"1760","article-title":"MDETR \u2013 modulated detection for end-to-end multi-modal understanding","author":"Kamath","year":"2021"},{"key":"10.1016\/j.neunet.2026.109721_bib0018","series-title":"Proceedings of the 38th international conference on machine learning","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume":"vol. 139","author":"Kim","year":"2021"},{"key":"10.1016\/j.neunet.2026.109721_bib0019","series-title":"Proceedings of the 40th international conference on machine learning","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume":"vol. 202","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.109721_bib0020","series-title":"Proceedings of the 39th international conference on machine learning (ICML)","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.109721_bib0021","unstructured":"Li, Z., Wang, M., Mei, J., & Liu, Y. (2021). MaIL: A unified mask-image-language trimodal network for referring image segmentation. arXiv preprint arXiv:2111.10747."},{"key":"10.1016\/j.neunet.2026.109721_bib0022","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2026.109721_bib0023","series-title":"European conference on computer vision (ECCV)","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.109721_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"GRES: Generalized referring expression segmentation","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109721_bib0025","series-title":"Proceedings of the IEEE international conference on computer vision (ICCV)","first-page":"1271","article-title":"Recurrent multimodal interaction for referring image segmentation","author":"Liu","year":"2017"},{"key":"10.1016\/j.neunet.2026.109721_bib0026","series-title":"Advances in neural information processing systems","first-page":"34892","article-title":"Visual instruction tuning","volume":"vol. 36","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109721_bib0027","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"779","article-title":"CARIS: Context-aware referring image segmentation","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109721_bib0028","series-title":"2015\u202fIEEE conference on computer vision and pattern recognition (CVPR)","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"10.1016\/j.neunet.2026.109721_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"7086","article-title":"Image segmentation using text and image prompts","author":"L\u00fcddecke","year":"2022"},{"key":"10.1016\/j.neunet.2026.109721_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"10034","article-title":"Multi-task collaborative network for joint referring expression comprehension and segmentation","author":"Luo","year":"2020"},{"key":"10.1016\/j.neunet.2026.109721_bib0031","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nature Communications"},{"key":"10.1016\/j.neunet.2026.109721_bib0032","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","article-title":"Generation and comprehension of unambiguous object descriptions","author":"Mao","year":"2016"},{"key":"10.1016\/j.neunet.2026.109721_bib0033","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision workshops (WACV workshops)","article-title":"SLVP: Self-supervised language-video pre-training for referring video object segmentation","author":"Mei","year":"2024"},{"key":"10.1016\/j.neunet.2026.109721_bib0034","series-title":"2016 Fourth international conference on 3D vision (3DV)","first-page":"565","article-title":"V-Net: Fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"10.1016\/j.neunet.2026.109721_bib0035","series-title":"Advances in neural information processing systems (NeurIPS)","article-title":"Unsupervised learning of dense visual representations","author":"Pinheiro","year":"2020"},{"key":"10.1016\/j.neunet.2026.109721_bib0036","series-title":"Proceedings of the 38th international conference on machine learning (ICML)","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.109721_bib0038","series-title":"Advances in neural information processing systems","first-page":"87310","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal LLMs","volume":"vol. 37","author":"Tong","year":"2024"},{"key":"10.1016\/j.neunet.2026.109721_bib0039","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.neunet.2026.109721_bib0040","series-title":"2021\u202fIEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"3023","article-title":"Dense contrastive learning for self-supervised visual pre-training","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109721_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128899","article-title":"Prompt-guided bidirectional deep fusion network for referring image segmentation","volume":"616","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109721_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10219","article-title":"PhraseCut: Language-based image segmentation in the wild","author":"Wu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109721_bib0043","doi-asserted-by":"crossref","unstructured":"Xiao, L., Yang, X., Peng, F., Wang, Y., & Xu, C. (2024). OneRef: Unified one-tower expression grounding and segmentation with mask referring modeling. arXiv preprint arXiv:2410.08021.","DOI":"10.52202\/079017-4438"},{"key":"10.1016\/j.neunet.2026.109721_bib0044","series-title":"Advances in neural information processing systems","first-page":"1890","article-title":"Voila-A: Aligning vision-language models with user's gaze attention","volume":"vol. 37","author":"Yan","year":"2024"},{"key":"10.1016\/j.neunet.2026.109721_bib0045","unstructured":"Yan, S., Zhu, T., Wang, Z., Cao, Y., Zhang, M., Ghosh, S., Wu, Y., & Yu, J. (2023a). VideoCoCa: Video-text modeling with zero-shot transfer from contrastive captioners. https:\/\/arxiv.org\/abs\/2212.04979."},{"key":"10.1016\/j.neunet.2026.109721_bib0046","doi-asserted-by":"crossref","unstructured":"Yan, Y., He, X., Chen, S., Lu, S., & Liu, J. (2024b). Fuse & calibrate: A bi-directional vision-language guided framework for referring image segmentation. https:\/\/arxiv.org\/abs\/2405.11205.","DOI":"10.1007\/978-981-97-5612-4_27"},{"key":"10.1016\/j.neunet.2026.109721_bib0047","series-title":"2022\u202fIEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"18134","article-title":"LAVT: Language-aware vision transformer for referring image segmentation","author":"Yang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109721_bib0048","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"10502","article-title":"Cross-modal self-attention network for referring image segmentation","author":"Ye","year":"2019"},{"issue":"20","key":"10.1016\/j.neunet.2026.109721_bib0049","doi-asserted-by":"crossref","first-page":"6539","DOI":"10.3390\/s24206539","article-title":"Semantic segmentation of satellite images for landslide detection using foreground-aware and multi-scale convolutional attention mechanism","volume":"24","author":"Yu","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.109721_bib0050","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","first-page":"1307","article-title":"MAttNet: Modular attention network for referring expression comprehension","author":"Yu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109721_bib0051","series-title":"European conference on computer vision (ECCV)","article-title":"Modeling context in referring expressions","author":"Yu","year":"2016"},{"key":"10.1016\/j.neunet.2026.109721_bib0052","unstructured":"Zhang, M., Liu, Y., Yin, X., Yue, H., & Yang, J. (2023). RISAM: Referring image segmentation via mutual-aware attention features. https:\/\/arxiv.org\/abs\/2311.15727."},{"key":"10.1016\/j.neunet.2026.109721_bib0053","article-title":"Augmented reality navigation method based on image segmentation and sensor tracking registration technology","volume":"14","author":"Zhang","year":"2024","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2026.109721_bib0054","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"14227","article-title":"GROUNDHOG: Grounding large language models to holistic segmentation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109721_bib0055","series-title":"Proceedings of the international conference on learning representations (ICLR)","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109721_bib0056","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"Generalized decoding for pixel, image, and language","author":"Zou","year":"2023"},{"key":"10.1016\/j.neunet.2026.109721_bib0037","doi-asserted-by":"crossref","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Wang, J., Wang, L., Gao, J., & Lee, Y. J. (2023). Segment everything everywhere all at once. https:\/\/arxiv.org\/abs\/2304.06718.","DOI":"10.52202\/075280-0868"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011767?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011767?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:50:59Z","timestamp":1793605859000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":56,"alternative-id":["S0893608026011767"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109721","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SegVLM: Deformable attentive visual enhancement for referring image segmentation using vision-language model","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109721","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109721"}}