{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:19:26Z","timestamp":1783145966923,"version":"3.54.6"},"reference-count":81,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":["62276108"],"award-info":[{"award-number":["62276108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.imavis.2026.106028","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T23:45:55Z","timestamp":1780616755000},"page":"106028","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["EVF-SAM: Early Vision-Language Fusion for text-prompted Segment Anything Model"],"prefix":"10.1016","volume":"173","author":[{"given":"Yuxuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianheng","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianghui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longjin","family":"Ran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6732-7823","authenticated-orcid":false,"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106028_b1","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, et al., Segment anything, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.imavis.2026.106028_b2","series-title":"Efficientsam: Leveraged masked image pretraining for efficient segment anything","author":"Xiong","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b3","series-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b4","series-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b5","article-title":"Segment anything in high quality","volume":"36","author":"Ke","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106028_b6","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14","first-page":"108","article-title":"Segmentation from natural language expressions","author":"Hu","year":"2016"},{"key":"10.1016\/j.imavis.2026.106028_b7","doi-asserted-by":"crossref","unstructured":"C. Liu, Z. Lin, X. Shen, J. Yang, X. Lu, A. Yuille, Recurrent multimodal interaction for referring image segmentation, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1271\u20131280.","DOI":"10.1109\/ICCV.2017.143"},{"key":"10.1016\/j.imavis.2026.106028_b8","doi-asserted-by":"crossref","unstructured":"H. Shi, H. Li, F. Meng, Q. Wu, Key-word-aware network for referring expression image segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 38\u201354.","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"10.1016\/j.imavis.2026.106028_b9","doi-asserted-by":"crossref","unstructured":"D.-J. Chen, S. Jia, Y.-C. Lo, H.-T. Chen, T.-L. Liu, See-through-text grouping for referring image segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 7454\u20137463.","DOI":"10.1109\/ICCV.2019.00755"},{"key":"10.1016\/j.imavis.2026.106028_b10","doi-asserted-by":"crossref","unstructured":"L. Ye, M. Rochan, Z. Liu, Y. Wang, Cross-modal self-attention network for referring image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10502\u201310511.","DOI":"10.1109\/CVPR.2019.01075"},{"key":"10.1016\/j.imavis.2026.106028_b11","doi-asserted-by":"crossref","unstructured":"Z. Hu, G. Feng, J. Sun, L. Zhang, H. Lu, Bi-directional relationship inferring network for referring image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 4424\u20134433.","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"10.1016\/j.imavis.2026.106028_b12","doi-asserted-by":"crossref","unstructured":"H. Ding, C. Liu, S. Wang, X. Jiang, Vision-language transformer and query generation for referring segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 16321\u201316330.","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"10.1016\/j.imavis.2026.106028_b13","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106028_b14","doi-asserted-by":"crossref","unstructured":"Z. Wang, Y. Lu, Q. Li, X. Tao, Y. Guo, M. Gong, T. Liu, Cris: Clip-driven referring image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11686\u201311695.","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"10.1016\/j.imavis.2026.106028_b15","doi-asserted-by":"crossref","unstructured":"Z. Yang, J. Wang, Y. Tang, K. Chen, H. Zhao, P.H. Torr, Lavt: Language-aware vision transformer for referring image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18155\u201318165.","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"10.1016\/j.imavis.2026.106028_b16","doi-asserted-by":"crossref","unstructured":"J. Liu, H. Ding, Z. Cai, Y. Zhang, R.K. Satzoda, V. Mahadevan, R. Manmatha, Polyformer: Referring image segmentation as sequential polygon generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18653\u201318663.","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"10.1016\/j.imavis.2026.106028_b17","series-title":"UniRef++: Segment every reference object in spatial and temporal spaces","author":"Wu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b18","series-title":"Universal segmentation at arbitrary granularity with language instruction","author":"Liu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b19","series-title":"CVPR","article-title":"Universal instance perception as object discovery and retrieval","author":"Yan","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b20","doi-asserted-by":"crossref","first-page":"14729","DOI":"10.52202\/068431-1071","article-title":"Coupalign: Coupling word-pixel with sentence-mask alignments for referring image segmentation","volume":"35","author":"Zhang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106028_b21","doi-asserted-by":"crossref","unstructured":"Y.X. Chng, H. Zheng, Y. Han, X. Qiu, G. Huang, Mask grounding for referring image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 26573\u201326583.","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"10.1016\/j.imavis.2026.106028_b22","series-title":"LISA: Reasoning segmentation via large language model","author":"Lai","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b23","series-title":"An improved baseline for reasoning segmentation with large language model","author":"Yang","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b24","series-title":"PixelLM: Pixel reasoning with large multimodal model","author":"Ren","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b25","series-title":"Perceptiongpt: Effectively fusing visual perception into llm","author":"Pi","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b26","series-title":"u-LLaVA: Unifying multi-modal tasks via large language model","author":"Xu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b27","series-title":"PSALM: Pixelwise SegmentAtion with large multi-modal model","author":"Zhang","year":"2024"},{"key":"10.1016\/j.imavis.2026.106028_b28","series-title":"GSVA: Generalized segmentation via multimodal large language models","author":"Xia","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b29","series-title":"Glamm: Pixel grounding large multimodal model","author":"Rasheed","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b30","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.imavis.2026.106028_b31","series-title":"Refsam: Efficiently adapting segmenting anything model for referring video object segmentation","author":"Li","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b32","series-title":"Image as a foreign language: Beit pretraining for all vision and vision-language tasks","author":"Wang","year":"2022"},{"key":"10.1016\/j.imavis.2026.106028_b33","doi-asserted-by":"crossref","unstructured":"S. Kazemzadeh, V. Ordonez, M. Matten, T. Berg, Referitgame: Referring to objects in photographs of natural scenes, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP, 2014, pp. 787\u2013798.","DOI":"10.3115\/v1\/D14-1086"},{"key":"10.1016\/j.imavis.2026.106028_b34","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part II 14","first-page":"69","article-title":"Modeling context in referring expressions","author":"Yu","year":"2016"},{"key":"10.1016\/j.imavis.2026.106028_b35","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11\u201314, 2016, Proceedings, Part IV 14","first-page":"792","article-title":"Modeling context between objects for referring expression understanding","author":"Nagaraja","year":"2016"},{"key":"10.1016\/j.imavis.2026.106028_b36","doi-asserted-by":"crossref","unstructured":"J. Mao, J. Huang, A. Toshev, O. Camburu, A.L. Yuille, K. Murphy, Generation and comprehension of unambiguous object descriptions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 11\u201320.","DOI":"10.1109\/CVPR.2016.9"},{"key":"10.1016\/j.imavis.2026.106028_b37","doi-asserted-by":"crossref","unstructured":"B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso, A. Torralba, Scene parsing through ade20k dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 633\u2013641.","DOI":"10.1109\/CVPR.2017.544"},{"key":"10.1016\/j.imavis.2026.106028_b38","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","article-title":"Semantic understanding of scenes through the ade20k dataset","volume":"127","author":"Zhou","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.imavis.2026.106028_b39","doi-asserted-by":"crossref","unstructured":"S. Shao, Z. Li, T. Zhang, C. Peng, G. Yu, X. Zhang, J. Li, J. Sun, Objects365: A large-scale, high-quality dataset for object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 8430\u20138439.","DOI":"10.1109\/ICCV.2019.00852"},{"key":"10.1016\/j.imavis.2026.106028_b40","doi-asserted-by":"crossref","unstructured":"X. Chen, R. Mottaghi, X. Liu, S. Fidler, R. Urtasun, A. Yuille, Detect what you can: Detecting and representing objects using holistic models and body parts, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1971\u20131978.","DOI":"10.1109\/CVPR.2014.254"},{"key":"10.1016\/j.imavis.2026.106028_b41","series-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105067","article-title":"Matte anything: Interactive natural image matting with segment anything model","volume":"147","author":"Yao","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106028_b43","series-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b44","doi-asserted-by":"crossref","unstructured":"Y. Sun, J. Chen, S. Zhang, X. Zhang, Q. Chen, G. Zhang, E. Ding, J. Wang, Z. Li, VRP-SAM: SAM with visual reference prompt, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 23565\u201323574.","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"10.1016\/j.imavis.2026.106028_b45","series-title":"Edit everything: A text-guided generative system for images editing","author":"Xie","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b46","series-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"10.1016\/j.imavis.2026.106028_b47","doi-asserted-by":"crossref","unstructured":"C. Shang, Z. Song, H. Qiu, L. Wang, F. Meng, H. Li, Prompt-driven referring image segmentation with instance contrasting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 4124\u20134134.","DOI":"10.1109\/CVPR52733.2024.00395"},{"key":"10.1016\/j.imavis.2026.106028_b48","series-title":"Visual Instruction Tuning","author":"Liu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b49","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.imavis.2026.106028_b50","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106028_b51","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.imavis.2026.106028_b52","series-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b53","series-title":"Generative pretraining in multimodality","author":"Sun","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b54","series-title":"Generative multimodal models are in-context learners","author":"Sun","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b55","doi-asserted-by":"crossref","unstructured":"J. Xu, X. Zhou, S. Yan, X. Gu, A. Arnab, C. Sun, X. Wang, C. Schmid, Pixel-Aligned Language Model, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 13030\u201313039.","DOI":"10.1109\/CVPR52733.2024.01238"},{"key":"10.1016\/j.imavis.2026.106028_b56","series-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b57","doi-asserted-by":"crossref","unstructured":"Y. Zhu, M. Zhu, N. Liu, Z. Xu, Y. Peng, Llava-phi: Efficient multi-modal assistant with small language model, in: Proceedings of the 1st International Workshop on Efficient Multimedia Computing under Limited, 2024, pp. 18\u201322.","DOI":"10.1145\/3688863.3689575"},{"key":"10.1016\/j.imavis.2026.106028_b58","series-title":"Textbooks are all you need ii: phi-1.5 technical report","author":"Li","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b59","series-title":"Introducing our multimodal models","author":"Bavishi","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b60","first-page":"52545","article-title":"Unveiling encoder-free vision-language models","volume":"37","author":"Diao","year":"2025","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106028_b61","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.imavis.2026.106028_b62","series-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"10.1016\/j.imavis.2026.106028_b63","series-title":"One-peace: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b64","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.imavis.2026.106028_b65","doi-asserted-by":"crossref","unstructured":"H. Caesar, J. Uijlings, V. Ferrari, Coco-stuff: Thing and stuff classes in context, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1209\u20131218.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"10.1016\/j.imavis.2026.106028_b66","doi-asserted-by":"crossref","unstructured":"V. Ramanathan, A. Kalia, V. Petrovic, Y. Wen, B. Zheng, B. Guo, R. Wang, A. Marquez, R. Kovvuri, A. Kadian, et al., Paco: Parts and attributes of common objects, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7141\u20137151.","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"10.1016\/j.imavis.2026.106028_b67","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.imavis.2026.106028_b68","doi-asserted-by":"crossref","unstructured":"C. Liu, H. Ding, X. Jiang, Gres: Generalized referring expression segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 23592\u201323601.","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"10.1016\/j.imavis.2026.106028_b69","doi-asserted-by":"crossref","unstructured":"X. Li, T. Wei, Y.P. Chen, Y.-W. Tai, C.-K. Tang, Fss-1000: A 1000-class dataset for few-shot segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 2869\u20132878.","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"10.1016\/j.imavis.2026.106028_b70","series-title":"European Conference on Computer Vision","first-page":"128","article-title":"Partimagenet: A large, high-quality dataset of parts","author":"He","year":"2022"},{"key":"10.1016\/j.imavis.2026.106028_b71","doi-asserted-by":"crossref","unstructured":"X. Liang, C. Xu, X. Shen, J. Yang, S. Liu, J. Tang, L. Lin, S. Yan, Human parsing with contextualized convolutional neural network, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1386\u20131394.","DOI":"10.1109\/ICCV.2015.163"},{"issue":"12","key":"10.1016\/j.imavis.2026.106028_b72","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1109\/TPAMI.2015.2408360","article-title":"Deep human parsing with active template regression","volume":"37","author":"Liang","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106028_b73","doi-asserted-by":"crossref","unstructured":"A. Kamath, M. Singh, Y. LeCun, G. Synnaeve, I. Misra, N. Carion, Mdetr-modulated detection for end-to-end multi-modal understanding, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 1780\u20131790.","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"10.1016\/j.imavis.2026.106028_b74","series-title":"Unsupervised cross-lingual representation learning at scale","author":"Conneau","year":"2019"},{"key":"10.1016\/j.imavis.2026.106028_b75","series-title":"DeepSpeed4Science initiative: Enabling large-scale scientific discovery through sophisticated AI system technologies","author":"Song","year":"2023"},{"key":"10.1016\/j.imavis.2026.106028_b76","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.imavis.2026.106028_b77","series-title":"OpenCLIP","author":"Ilharco","year":"2021"},{"key":"10.1016\/j.imavis.2026.106028_b78","series-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"10.1016\/j.imavis.2026.106028_b79","doi-asserted-by":"crossref","unstructured":"H. Liu, C. Li, Y. Li, Y.J. Lee, Improved baselines with visual instruction tuning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 26296\u201326306.","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"10.1016\/j.imavis.2026.106028_b80","doi-asserted-by":"crossref","unstructured":"J. Johnson, B. Hariharan, L. Van Der Maaten, L. Fei-Fei, C. Lawrence Zitnick, R. Girshick, Clevr: A diagnostic dataset for compositional language and elementary visual reasoning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2901\u20132910.","DOI":"10.1109\/CVPR.2017.215"},{"key":"10.1016\/j.imavis.2026.106028_b81","doi-asserted-by":"crossref","unstructured":"D.A. Hudson, C.D. Manning, Gqa: A new dataset for real-world visual reasoning and compositional question answering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 6700\u20136709.","DOI":"10.1109\/CVPR.2019.00686"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001356?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001356?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:49:38Z","timestamp":1783144178000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626001356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":81,"alternative-id":["S0262885626001356"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106028","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"EVF-SAM: Early Vision-Language Fusion for text-prompted Segment Anything Model","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106028","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":"106028"}}