{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:30:41Z","timestamp":1764588641872,"version":"build-2065373602"},"reference-count":102,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11263-025-02517-0","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T10:20:27Z","timestamp":1753957227000},"page":"7460-7485","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Segment Anything in Context with Vision Foundation Models"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8540-9154","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3243-2356","authenticated-orcid":false,"given":"Muzhi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-614X","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-7976","authenticated-orcid":false,"given":"Xinlong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0709-7903","authenticated-orcid":false,"given":"Bo","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3123-6043","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5335-7010","authenticated-orcid":false,"given":"Shiyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6540-1811","authenticated-orcid":false,"given":"Raviteja","family":"Vemulapalli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,31]]},"reference":[{"key":"2517_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, S., Zhou, C., Lewis, M., Zettlemoyer, L., & Ghazvininejad, M. (2022.) In-context examples selection for machine translation, arXiv:2212.02437","DOI":"10.18653\/v1\/2023.findings-acl.564"},{"key":"2517_CR2","unstructured":"Arthur, D., & Vassilvitskii, S. (2007). K-means++ the advantages of careful seeding, in Proc. Ann. ACM SIAM Symp. on Disc. Algo., pp. 1027\u20131035."},{"key":"2517_CR3","unstructured":"Bai, H., Mou, S., Likhomanenko, T., Cinbis, R. G., Tuzel, O., Huang, P., Shan, J., Shi, J., & Cao, M. (2023). Vision datasets: A benchmark for vision-based industrial inspection, arXiv:2306.07890."},{"key":"2517_CR4","unstructured":"Bao, H., Dong, L., Piao, S., & Wei, F. (2021). Beit: Bert pre-training of image transformers, arXiv:2106.08254."},{"key":"2517_CR5","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., & Efros, A. (2022). Visual prompting via image inpainting, in Proc. Adv. Neural Inf. Process. Syst., vol. 35, pp. 25\u00a0005\u201325\u00a0017."},{"key":"2517_CR6","unstructured":"A. Blattmann, R. Rombach, K. Oktay, J. M\u00fcller, and B. Ommer, Retrieval-augmented diffusion models, in Proc. Adv. Neural Inf. Process. Syst., vol. 35, 2022, pp. 15\u00a0309\u201315\u00a0324."},{"key":"2517_CR7","unstructured":"Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021). On the opportunities and risks of foundation models, arXiv:2108.07258."},{"key":"2517_CR8","doi-asserted-by":"crossref","unstructured":"Bonneel, N., Van De Panne, M., Paris, S., & Heidrich, W. (2011). Displacement interpolation using lagrangian mass transport, in Proc. of the SIGGRAPH Asia conf., pp. 1\u201312.","DOI":"10.1145\/2024156.2024192"},{"key":"2517_CR9","unstructured":"Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., Van Den Driessche, G. B., Lespiau, J.-B., Damoc, B., Clark, A., et al. (2022). Improving language models by retrieving from trillions of tokens, in Proc. Int. Conf. Mach. Learn., pp. 2206\u20132240."},{"key":"2517_CR10","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners, in Proc. Adv. Neural Inf. Process. Syst., vol. 33, pp. 1877\u20131901."},{"issue":"2","key":"2517_CR11","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1109\/TMI.2013.2290491","volume":"33","author":"S Candemir","year":"2013","unstructured":"Candemir, S., Jaeger, S., Palaniappan, K., Musco, J. P., Singh, R. K., Xue, Z., Karargyris, A., Antani, S., Thoma, G., & McDonald, C. J. (2013). Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE transactions on medical imaging, 33(2), 577\u2013590.","journal-title":"IEEE transactions on medical imaging"},{"key":"2517_CR12","doi-asserted-by":"crossref","unstructured":"Cao, Q., Chen, Y., Ma, C., & Yang, X. (2023). Few-shot rotation-invariant aerial image semantic segmentation, IEEE Trans. on Geosci. and Remote Sens., vol. 62, pp. 1\u201313,","DOI":"10.1109\/TGRS.2023.3338699"},{"key":"2517_CR13","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers, in Int. Conf. Comput. Vis., pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2517_CR14","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations, in Proc. Int. Conf. Mach. Learn., pp. 1597\u20131607."},{"key":"2517_CR15","doi-asserted-by":"crossref","unstructured":"Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., & Yuille, A. (2014). Detect what you can: Detecting and representing objects using holistic models and body parts, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 1971\u20131978.","DOI":"10.1109\/CVPR.2014.254"},{"key":"2517_CR16","doi-asserted-by":"crossref","unstructured":"Cheng, H. K., & Schwing, A. G. (2022). Xmem: Long-term video object segmentation with an atkinson-shiffrin memory model, in Eur. Conf. Comput. Vis., pp. 640\u2013658.","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"2517_CR17","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A. G., Kirillov, A., & Girdhar, R. (2022). Masked-attention mask transformer for universal image segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 1290\u20131299.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2517_CR18","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022). Palm: Scaling language modeling with pathways, arXiv:2204.02311."},{"key":"2517_CR19","unstructured":"Codella, N., Rotemberg, V., Tschandl, P., Celebi, M. E., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., Marchetti, M., et al. (2019) Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration, arXiv:1902.03368."},{"key":"2517_CR20","doi-asserted-by":"crossref","unstructured":"Demir, I., Koperski, K., Lindenbaum, D., Pang, G., Huang, J., Basu, S., Hughes, F., Tuia, D., & Raskar, R. (2018). Deepglobe 2018: A challenge to parse the earth through satellite images, in IEEE Conf. Comput. Vis. Pattern Recog. Worksh., pp. 172\u2013181.","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"2517_CR21","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding, in Nor. Amer. Chap. of the ACL, pp. 4171\u20134186."},{"key":"2517_CR22","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale, in Int","author":"A Dosovitskiy","year":"2020","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale, in Int. Represent: Conf. Learn."},{"key":"2517_CR23","unstructured":"Esser, P., Rombach, R., & Ommer, B. (2021). Taming transformers for high-resolution image synthesis, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 12\u00a0873\u201312\u00a0883."},{"key":"2517_CR24","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. Int. J. Comput. Vis., 88, 303\u2013338.","journal-title":"Int. J. Comput. Vis."},{"key":"2517_CR25","doi-asserted-by":"crossref","unstructured":"Fang, Y., Wang, W., Xie, B., Sun, Q., Wu, L., Wang, X., Huang, T., Wang, X., & Cao, Y. (2023). Eva: Exploring the limits of masked visual representation learning at scale, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 19\u00a0358\u201319\u00a0369.","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"2517_CR26","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., & Girshick, R. (2019). Lvis: A dataset for large vocabulary instance segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 5356\u20135364.","DOI":"10.1109\/CVPR.2019.00550"},{"key":"2517_CR27","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M. (2020). Retrieval augmented language model pre-training, in Proc. Int. Conf. Mach. Learn., pp. 3929\u20133938."},{"key":"2517_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 16\u00a0000\u201316\u00a0009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2517_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2517_CR30","doi-asserted-by":"crossref","unstructured":"Hong, S., Cho, S., Nam, J., Lin, S., & Kim, S. (2022). Cost aggregation with 4d convolutional swin transformer for few-shot segmentation, in Eur. Conf. Comput. Vis., pp. 108\u2013126.","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"2517_CR31","unstructured":"Iqbal, E., Safarov, S., and Bang, S. (2022). Msanet: Multi-similarity and attention guidance for boosting few-shot segmentation, arXiv:2206.09667."},{"issue":"2","key":"2517_CR32","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1109\/TMI.2013.2284099","volume":"33","author":"S Jaeger","year":"2013","unstructured":"Jaeger, S., Karargyris, A., Candemir, S., Folio, L., Siegelman, J., Callaghan, F., Xue, Z., Palaniappan, K., Singh, R. K., Antani, S., et al. (2013). Automatic tuberculosis screening using chest radiographs. IEEE transactions on medical imaging, 33(2), 233\u2013245.","journal-title":"IEEE transactions on medical imaging"},{"key":"2517_CR33","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M. T., Hassani, A., Orlov, N., & Shi, H. (2023). Oneformer: One transformer to rule universal image segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 2989\u20132998.","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"2517_CR34","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q., Sung, Y.-H., Li, Z., & Duerig, T. (2021). Scaling up visual and vision-language representation learning with noisy text supervision, in Proc. Int. Conf. Mach. Learn., pp. 4904\u20134916."},{"issue":"3","key":"2517_CR35","doi-asserted-by":"publisher","first-page":"2652","DOI":"10.1609\/aaai.v38i3.28043","volume":"38","author":"C Jing","year":"2024","unstructured":"Jing, C., Li, Y., Chen, H., & Shen, C. (2024). Retrieval-augmented primitive representations for compositional zero-shot learning. AAAI, 38(3), 2652\u20132660.","journal-title":"AAAI"},{"key":"2517_CR36","doi-asserted-by":"crossref","unstructured":"Johnander, J., Danelljan, M., Brissman, E., Khan, F. S., & Felsberg, M. (2019). A generative appearance model for end-to-end video object segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 8953\u20138962.","DOI":"10.1109\/CVPR.2019.00916"},{"key":"2517_CR37","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., O\u011fuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering, arXiv:2004.04906.","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"2517_CR38","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023). Segment anything, in Int. Conf. Comput. Vis., pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2517_CR39","unstructured":"Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners, in Proc. Adv. Neural Inf. Process. Syst., vol. 35, pp. 22\u00a0199\u201322\u00a0213."},{"key":"2517_CR40","doi-asserted-by":"crossref","unstructured":"Lei, S., Zhang, X., He, J., Chen, F., Du, B., & Lu, C.-T. (2022). Cross-domain few-shot semantic segmentation, in Eur. Conf. Comput. Vis., pp. 73\u201390.","DOI":"10.1007\/978-3-031-20056-4_5"},{"key":"2517_CR41","doi-asserted-by":"crossref","unstructured":"Li, X. L., & Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation, arXiv:2101.00190.","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"2517_CR42","unstructured":"Li, F., Jiang, Q., Zhang, H., Ren, T., Liu, S., Zou, X., Xu, H., Li, H., Yang, J., Li, C., et al. (2024). Visual in-context prompting, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 12\u00a0861\u201312\u00a0871."},{"key":"2517_CR43","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, T., Chen, Y. P., Tai, Y.-W., & Tang, C.-K. (2020). Fss-1000: A 1000-class dataset for few-shot segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 2869\u20132878.","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"2517_CR44","unstructured":"Li, X., Yuan, H., Li, W., Ding, H., Wu, S., Zhang, W., Li, Y., Chen, K., & Loy, C. C. (2024). Omg-seg: Is one model good enough for all segmentation? in IEEE Conf. Comput. Vis. Pattern Recog., pp. 27\u00a0948\u201327\u00a0959."},{"key":"2517_CR45","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Sun, P., Zou, X., Liu, S., Yang, J., Li, C., Zhang, L., & Gao, J. (2023). Semantic-sam: Segment and recognize anything at any granularity, arXiv:2307.04767.","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"2517_CR46","unstructured":"Liang, Y., Li, X., Jafari, N., & Chen, J. (2020). Video object segmentation with adaptive feature bank and uncertain-region refinement, in Proc. Adv. Neural Inf. Process. Syst., vol. 33, pp. 3430\u20133441."},{"key":"2517_CR47","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context, in Eur. Conf. Comput. Vis., pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2517_CR48","doi-asserted-by":"crossref","unstructured":"Lin, H., Qi, X., & Jia, J. (2019). Agss-vos: Attention guided single-shot video object segmentation, in Int. Conf. Comput. Vis., pp. 3949\u20133957.","DOI":"10.1109\/ICCV.2019.00405"},{"key":"2517_CR49","doi-asserted-by":"crossref","unstructured":"Lin, Z., Yang, T., Li, M., Wang, Z., Yuan, C., Jiang, W., & Liu, W. (2022). Swem: Towards real-time video object segmentation with sequential weighted expectation-maximization, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 1362\u20131372.","DOI":"10.1109\/CVPR52688.2022.00142"},{"key":"2517_CR50","unstructured":"Liu, Y., Jing, C., Li, H., Zhu, M., Chen, H., Wang, X., & Shen, C. (2024). A simple image segmentation framework via in-context examples, arXiv:2410.04842."},{"key":"2517_CR51","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach, arXiv:1907.11692."},{"key":"2517_CR52","doi-asserted-by":"crossref","unstructured":"Liu, J., Shen, D., Zhang, Y., Dolan, B., Carin, L., & Chen, W. (2021). What makes good in-context examples for gpt-$$3 $$? arXiv:2101.06804.","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"2517_CR53","doi-asserted-by":"crossref","unstructured":"Liu, X., Shi, G., Wang, R., Lai, Y., Zhang, J., Sun, L., Yang, Q., Wu, Y., Li, M., Han, W., et al. (2024) Feature-prompting gbmseg: One-shot reference guided training-free prompt engineering for glomerular basement membrane segmentation, arXiv:2406.16271.","DOI":"10.1007\/978-3-031-72114-4_27"},{"key":"2517_CR54","unstructured":"Liu, Y., Zhu, M., Li, H., Chen, H., Wang, X., & Shen, C. (2023). Matcher: Segment anything with one shot using all-purpose feature matching, arXiv:2305.13310."},{"key":"2517_CR55","unstructured":"Liu, Y., Zhu, M., Li, H., Chen, H., Wang, X., & Shen, C. (2024). Matcher: Segment anything with one shot using all-purpose feature matching, in The Twelfth International Conference on Learning Representations. [Online]. Available: https:\/\/openreview.net\/forum?id=yzRXdhk2he"},{"issue":"2","key":"2517_CR56","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1007\/s11263-024-02204-6","volume":"133","author":"Y Liu","year":"2025","unstructured":"Liu, Y., Wang, X., Zhu, M., Cao, Y., Huang, T., & Shen, C. (2025). Masked channel modeling for bootstrapping visual pre-training. Int. J. Comput. Vis., 133(2), 760\u2013780.","journal-title":"Int. J. Comput. Vis."},{"key":"2517_CR57","doi-asserted-by":"crossref","unstructured":"Long, A., Yin, W., Ajanthan, T., Nguyen, V., Purkait, P., Garg, R., Blair, A., Shen, C., & van den Hengel, A. (2022). Retrieval augmented classification for long-tail visual recognition, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 6959\u20136969.","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"2517_CR58","doi-asserted-by":"crossref","unstructured":"Meng, L., Lan, S., Li, H., Alvarez, J. M., Wu, Z., & Jiang, Y.-G. (2023). Segic: Unleashing the emergent correspondence for in-context segmentation, arXiv:2311.14671,","DOI":"10.1007\/978-3-031-72920-1_12"},{"key":"2517_CR59","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., & Cho, M. (2021). Hypercorrelation squeeze for few-shot segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 6941\u20136952.","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"2517_CR60","unstructured":"Morabia, K., Arora, J., & Vijaykumar, T. (2020). Attention-based joint detection of object and semantic part, arXiv:2007.02419."},{"key":"2517_CR61","doi-asserted-by":"crossref","unstructured":"Nguyen, K., & Todorovic, S. (2019). Feature weighting and boosting for few-shot segmentation, in Int. Conf. Comput. Vis., pp. 622\u2013631.","DOI":"10.1109\/ICCV.2019.00071"},{"key":"2517_CR62","unstructured":"OpenAI, Gpt-4 technical report, arXiv:2303.08774, (2023)."},{"key":"2517_CR63","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et al. (2023). Dinov2: Learning robust visual features without supervision, arXiv:2304.07193."},{"key":"2517_CR64","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022). Training language models to follow instructions with human feedback, in Proc. Adv. Neural Inf. Process. Syst., vol. 35, pp. 27\u00a0730\u201327\u00a0744."},{"key":"2517_CR65","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., & Sorkine-Hornung, A. (2016). A benchmark dataset and evaluation methodology for video object segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 724\u2013732.","DOI":"10.1109\/CVPR.2016.85"},{"key":"2517_CR66","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., & Van Gool, L. (2017). The 2017 davis challenge on video object segmentation, arXiv:1704.00675."},{"key":"2517_CR67","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021). Learning transferable visual models from natural language supervision, in Proc. Int. Conf. Mach. Learn., pp. 8748\u20138763."},{"key":"2517_CR68","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Kalia, A., Petrovic, V., Wen, Y., Zheng, B., Guo, B., Wang, R., Marquez, A., Kovvuri, R., Kadian, A., et al. (2023). Paco: Parts and attributes of common objects, arXiv:2301.01795.","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"2517_CR69","doi-asserted-by":"crossref","unstructured":"Rubin, O., Herzig, J., & Berant, J. (2021). Learning to retrieve prompts for in-context learning, arXiv:2112.08633.","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"2517_CR70","volume-title":"One-shot learning for semantic segmentation, in Brit","author":"A Shaban","year":"2017","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., & Boots, B. (2017). One-shot learning for semantic segmentation, in Brit. Conf: Mach. Vis."},{"key":"2517_CR71","unstructured":"Shuai, C., Fanman, M., Runtong, Z., Heqian, Q., Hongliang, L., Qingbo, W., & Linfeng, X. (2023). Visual and textual prior guided mask assemble for few-shot segmentation and beyond, arXiv:2308.07539."},{"key":"2517_CR72","unstructured":"Su, J., Fan, Q., Pei, W., Lu, G., & Chen, F. (2024). Domain-rectifying adapter for cross-domain few-shot segmentation, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 24\u00a0036\u201324\u00a0045."},{"key":"2517_CR73","unstructured":"Sun, Y., Chen, Q., Wang, J., Wang, J. & Li, Z. (2023). Exploring effective factors for improving visual in-context learning, arXiv:2304.04748."},{"key":"2517_CR74","unstructured":"Sun, Y., Chen, J., Zhang, S., Zhang, X., Chen, Q., Zhang, G., Ding, E., Wang, J., & Li, Z. (2024). Vrp-sam: Sam with visual reference prompt, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 23\u00a0565\u201323\u00a0574."},{"issue":"2","key":"2517_CR75","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","volume":"44","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., & Jia, J. (2020). Prior guided feature enrichment network for few-shot segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 44(2), 1050\u20131065.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2517_CR76","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023). Llama: Open and efficient foundation language models, arXiv:2302.13971."},{"issue":"1","key":"2517_CR77","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl, P., Rosendahl, C., & Kittler, H. (2018). The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data, 5(1), 1\u20139.","journal-title":"Scientific data"},{"key":"2517_CR78","first-page":"30","volume-title":"Attention is all you need, in Proc","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141, & Polosukhin, I. (2017). Attention is all you need, in Proc (p. 30). Adv: Neural Inf. Process. Syst., vol."},{"key":"2517_CR79","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J. H., Zou, Y., Zhou, D., & Feng, J. (2019). Panet: Few-shot image semantic segmentation with prototype alignment, in Int. Conf. Comput. Vis., pp. 9197\u20139206.","DOI":"10.1109\/ICCV.2019.00929"},{"key":"2517_CR80","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., & Huang, T. (2023). Images speak in images: A generalist painter for in-context visual learning, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 6830\u20136839.","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"2517_CR81","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., & Huang, T. (2023). Seggpt: Towards segmenting everything in context, in Int. Conf. Comput. Vis., pp. 1130\u20131140.","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"2517_CR82","unstructured":"Waqas Zamir, S., Arora, A., Gupta, A., Khan, S., Sun, G., Shahbaz Khan, F., Zhu, F., Shao, L., Xia, G.-S., & Bai, X. (2019). isaid: A large-scale dataset for instance segmentation in aerial images, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 28\u201337."},{"key":"2517_CR83","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. (2022) Chain-of-thought prompting elicits reasoning in large language models, in Proc. Adv. Neural Inf. Process. Syst., vol. 35, pp. 24\u00a0824\u201324\u00a0837."},{"key":"2517_CR84","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., & Hu, H. (2022). Simmim: A simple framework for masked image modeling, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 9653\u20139663.","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"2517_CR85","unstructured":"Xu, C., Liu, C., Wang, Y., & Fu, Y. (2024). Towards global optimal visual in-context learning prompt selection, arXiv:2405.15279."},{"key":"2517_CR86","doi-asserted-by":"crossref","unstructured":"Xu, N., Yang, L., Fan, Y., Yang, J., Yue, D., Liang, Y., Price, B., Cohen, S., & Huang, T. (2018). Youtube-vos: Sequence-to-sequence video object segmentation, in Eur. Conf. Comput. Vis., pp. 585\u2013601.","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"2517_CR87","unstructured":"Yan, B., Jiang, Y., Wu, J., Wang, D., Luo, P., Yuan, Z., & Lu, H. (2023). Universal instance perception as object discovery and retrieval, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 15\u00a0325\u201315\u00a0336."},{"key":"2517_CR88","unstructured":"Yang, Z., Wei, Y., & Yang, Y. (2021). Associating objects with transformers for video object segmentation, in Proc. Adv. Neural Inf. Process. Syst., vol. 34, pp. 2491\u20132502."},{"key":"2517_CR89","doi-asserted-by":"crossref","unstructured":"X. Yao, Q. Cao, X. Feng, G. Cheng, and J. Han, 2021 Scale-aware detailed matching for few-shot aerial image semantic segmentation, IEEE Trans. on Geosci. and Remote Sens., 60, 1\u201311, .","DOI":"10.1109\/TGRS.2021.3119852"},{"key":"2517_CR90","doi-asserted-by":"crossref","unstructured":"Ye, X., Iyer, S., Celikyilmaz, A., Stoyanov, V., Durrett, G., & Pasunuru, R. (2022). Complementary explanations for effective in-context learning, arXiv:2211.13892.","DOI":"10.18653\/v1\/2023.findings-acl.273"},{"key":"2517_CR91","unstructured":"Zeng, A., Liu, X., Du, Z., Wang, Z., Lai, H., Ding, M., Yang, Z., Xu, Zheng, Y.W., Xia, X., et al. (2022). Glm-130b: An open bilingual pre-trained model, arXiv:2210.02414."},{"key":"2517_CR92","unstructured":"Zhang, A., Gao, G., Jiao, J., Liu, C., & Wei, Y. (2024). Bridge the points: Graph-based few-shot segment anything semantically, in Proc. Adv. Neural Inf. Process. Syst., vol. 37, pp. 33\u00a0232\u201333\u00a0261."},{"key":"2517_CR93","unstructured":"Zhang, R., Jiang, Z., Guo, Z., Yan, S., Pan, J., Dong, H., Gao, P., & Li, H. (2023). Personalize segment anything model with one shot, arXiv:2305.03048."},{"key":"2517_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, G., Liu, F., Yao, R., & Shen, C. (2019). Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 5217\u20135226.","DOI":"10.1109\/CVPR.2019.00536"},{"key":"2517_CR95","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X. V., et al. (2022). Opt: Open pre-trained transformer language models, arXiv:2205.01068."},{"key":"2517_CR96","unstructured":"Zhang, J.-W., Sun, Y., Yang, Y., & Chen, W. (2022). Feature-proxy transformer for few-shot segmentation, in Proc. Adv. Neural Inf. Process. Syst., vol. 35, pp. 6575\u20136588."},{"key":"2517_CR97","unstructured":"Zhang, Y., Zhou, K., & Liu, Z. (2023). What makes good examples for visual in-context learning? in Proc. Adv. Neural Inf. Process. Syst., vol. 36, pp. 17\u00a0773\u201317\u00a0794."},{"key":"2517_CR98","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., & Kong, T. (2021). ibot: Image bert pre-training with online tokenizer, arXiv:2111.07832."},{"key":"2517_CR99","doi-asserted-by":"crossref","unstructured":"Zhu, M., Li, H., Chen, H., Fan, C., Mao, W., Jing, C., Liu, Y., & Shen, C. (2023). Segprompt: Boosting open-world segmentation via category-level prompt learning, in Int. Conf. Comput. Vis., pp. 999\u20131008.","DOI":"10.1109\/ICCV51070.2023.00098"},{"key":"2517_CR100","unstructured":"Zhu, M., Liu, Y., Luo, Z., Jing, C., Chen, H., Xu, G., Wang, X., & Shen, C. (2024). Unleashing the potential of the diffusion model in few-shot semantic segmentation, arXiv:2410.02369."},{"key":"2517_CR101","unstructured":"Zou, X., Dou, Z.-Y., Yang, J., Gan, Z., Li, L., Li, C., Dai, X., Behl, H., Wang, J., Yuan, L., et al. (2023). Generalized decoding for pixel, image, and language, in IEEE Conf. Comput. Vis. Pattern Recog., pp. 15\u00a0116\u201315\u00a0127."},{"key":"2517_CR102","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Gao, J., & Lee, Y. J. (2023). Segment everything everywhere all at once, in Proc. Adv. Neural Inf. Process. Syst., vol. 36, pp. 19\u00a0769\u201319\u00a0782."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02517-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02517-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02517-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T08:54:49Z","timestamp":1760086489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02517-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":102,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["2517"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02517-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"assertion":[{"value":"10 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}