{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:01:06Z","timestamp":1792789266045,"version":"4.5.0"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T00:00:00Z","timestamp":1721088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T00:00:00Z","timestamp":1721088000000},"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":[[2025,1]]},"DOI":"10.1007\/s11263-024-02185-6","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T19:01:49Z","timestamp":1721156509000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Towards Training-Free Open-World Segmentation via Image Prompt Foundation Models"],"prefix":"10.1007","volume":"133","author":[{"given":"Lv","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng-Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoke","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7817-0665","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,16]]},"reference":[{"key":"2185_CR1","unstructured":"Angus, M., Czarnecki, K., & Salay, R. (2019). Efficacy of pixel-level ood detection for semantic segmentation. arXiv preprint arXiv:1911.02897"},{"key":"2185_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2185_CR3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.00817","author":"M Bucher","year":"2019","unstructured":"Bucher, M., Vu, T. H., Cord, M., et al. (2019). Zero-shot semantic segmentation. Advances in Neural Information Processing Systems. https:\/\/doi.org\/10.48550\/arXiv.1906.00817","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2185_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, JRR. & Ferrari, V. (2018). Coco-stuff: Thing and stuff classes in context. In: Proceedings of the IEEE conference on computer vision and pattern recognition, computer vision foundation \/ IEEE computer society, pp 1209\u20131218","DOI":"10.1109\/CVPR.2018.00132"},{"key":"2185_CR5","doi-asserted-by":"crossref","unstructured":"Cen, J., Yun, P., Cai, J., et al. (2021). Deep metric learning for open world semantic segmentation. In International conference on computer vision , pp 15,333\u201315,342","DOI":"10.1109\/ICCV48922.2021.01505"},{"key":"2185_CR6","unstructured":"Cen, J., Zhou, Z., Fang, J., et al. (2023). Segment anything in 3d with nerfs. arXiv preprint arXiv:2304.12308"},{"key":"2185_CR7","doi-asserted-by":"crossref","unstructured":"Cha, J., Mun, J., & Roh, B. (2023). Learning to generate text-grounded mask for open-world semantic segmentation from only image-text pairs. In Conference on computer vision and pattern recognition IEEE, pp 11,165\u201311,174","DOI":"10.1109\/CVPR52729.2023.01074"},{"issue":"4","key":"2185_CR8","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., et al. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2185_CR9","unstructured":"Chen, T., Mai, Z., Li, R., et al. (2023). Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation. arXiv preprint arXiv:2305.05803"},{"key":"2185_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, J., Nandi, S., Natarajan, P., et al. (2021). SIGN: Spatial-information incorporated generative network for generalized zero-shot semantic segmentation. In International conference on computer vision IEEE, pp 9536\u20139546","DOI":"10.1109\/ICCV48922.2021.00942"},{"key":"2185_CR11","unstructured":"Cheng, Y., Li, L., Xu, Y., et al. (2023). Segment and track anything. arXiv preprint arXiv:2305.06558"},{"issue":"240","key":"2185_CR12","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., Narang, S., Devlin, J., et al. (2023). Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240), 1\u2013113.","journal-title":"Journal of Machine Learning Research"},{"key":"2185_CR13","doi-asserted-by":"crossref","unstructured":"Cui, Z., Longshi, W., & Wang, R. (2020). Open set semantic segmentation with statistical test and adaptive threshold. In 2020 IEEE International conference on multimedia and expo (ICME), IEEE, pp 1\u20136","DOI":"10.1109\/ICME46284.2020.9102712"},{"key":"2185_CR14","unstructured":"Dai, W., Li, J., Li, D., et al. (2023). Instructblip: Towards general-purpose vision-language models with instruction tuning. CoRR abs\/2305.06500"},{"key":"2185_CR15","unstructured":"Devlin, J., Chang, MW., Lee, K., et al. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"issue":"2","key":"2185_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L. V., Williams, C. K. I., et al. (2010). The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"2185_CR17","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Gu, X., Cui, Y., et al. (2022). Scaling open-vocabulary image segmentation with image-level labels. In European conference on computer vision, vol 13696. Springer, pp 540\u2013557","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"2185_CR18","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhou, S., Niu, L., et al. (2020). Context-aware feature generation for zero-shot semantic segmentation. In Proceedings of the 28th ACM international conference on multimedia, pp 1921\u20131929","DOI":"10.1145\/3394171.3413593"},{"key":"2185_CR19","unstructured":"Guo, J., Hao, Z., Wang, C., et al. (2024). Data-efficient large vision models through sequential autoregression. arXiv preprint arXiv:2402.04841"},{"key":"2185_CR20","doi-asserted-by":"crossref","unstructured":"Gupta, A., Doll\u00e1r, P., & Girshick, RB. (2019). LVIS: A dataset for large vocabulary instance segmentation. In CVPR computer vision foundation \/ IEEE, pp 5356\u20135364","DOI":"10.1109\/CVPR.2019.00550"},{"key":"2185_CR21","doi-asserted-by":"crossref","unstructured":"Hammam, A., Bonarens, F., Ghobadi, SE., et al. (2023). Identifying out-of-domain objects with dirichlet deep neural networks. In International conference on computer vision, pp 4560\u20134569","DOI":"10.1109\/ICCVW60793.2023.00490"},{"key":"2185_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., et al. (2022). Masked autoencoders are scalable vision learners. In Conference on computer vision and pattern recognition, pp 16,000\u201316,009","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2185_CR23","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2185_CR24","unstructured":"Jiang, PT., & Yang, Y. (2023). Segment anything is a good pseudo-label generator for weakly supervised semantic segmentation. arXiv preprint arXiv:2305.01275"},{"key":"2185_CR25","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., et al. (2023). Segment anything. arXiv preprint arXiv:2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2185_CR26","unstructured":"Li. J., Li, D., Xiong, C., et al. (2022). BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning, Proceedings of Machine Learning Research, PMLR, vol 162, pp 12,888\u201312,900"},{"key":"2185_CR27","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, T., Chen, YP., et al. (2020). FSS-1000: A 1000-class dataset for few-shot segmentation. In Conference on computer vision and pattern recognition, Computer vision foundation \/ IEEE, pp 2866\u20132875","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"2185_CR28","doi-asserted-by":"crossref","unstructured":"Liang, F., Wu, B., Dai, X., et al. (2023). Open-vocabulary semantic segmentation with mask-adapted CLIP. In Conference on computer vision and pattern recognition. IEEE, pp 7061\u20137070","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"2185_CR29","unstructured":"Liu, H., Li, C., Wu, Q., et al. (2023a). Visual instruction tuning. CoRR abs\/2304.08485"},{"key":"2185_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wen, Y., Han, J., et al. (2022). Open-world semantic segmentation via contrasting and clustering vision-language embedding. European conference on computer vision, Springer, pp. 275\u2013292","DOI":"10.1007\/978-3-031-20044-1_16"},{"key":"2185_CR31","unstructured":"Liu, Y., Zhu, M., Li, H., et al. (2023b). Matcher: Segment anything with one shot using all-purpose feature matching. arXiv preprint arXiv:2305.13310"},{"key":"2185_CR32","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2185_CR33","unstructured":"Lu, J., Batra, D., Parikh, D., et al. (2019). Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in Neural Information Processing Systems, 32"},{"key":"2185_CR34","unstructured":"Luo, H., Bao, J., Wu, Y., et al. (2023). Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation. International Conference on Machine Learning, PMLR, pp. 23033\u201323044"},{"key":"2185_CR35","unstructured":"Ma, C., Yang, Y., Wang, Y., et al. (2022). Open-vocabulary semantic segmentation with frozen vision-language models. arXiv preprint arXiv:2210.15138"},{"key":"2185_CR36","unstructured":"Morabia, K., Arora, J., & Vijaykumar, T. (2020). Attention-based joint detection of object and semantic part. CoRR abs\/2007.02419"},{"key":"2185_CR37","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., et al. (2014). The role of context for object detection and semantic segmentation in the wild. In Conference on computer vision and pattern recognition. IEEE Computer Society, pp 891\u2013898","DOI":"10.1109\/CVPR.2014.119"},{"key":"2185_CR38","doi-asserted-by":"crossref","unstructured":"Nguyen, K., & Todorovic, S. (2019). Feature weighting and boosting for few-shot segmentation. In International conference on computer vision, IEEE, pp 622\u2013631","DOI":"10.1109\/ICCV.2019.00071"},{"key":"2185_CR39","doi-asserted-by":"crossref","unstructured":"Oin, J., Wu, J., Yan, P., et al. (2023). Freeseg: Unified, universal and open-vocabulary image segmentation. In Conference on computer vision and pattern recognition. IEEE, pp 19,446\u201319,455","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"2185_CR40","unstructured":"Oquab, M., Darcet, T., & Th\u00e9o\u00a0Moutakanni, ea. (2023). Dinov2: Learning robust visual features without supervision. CoRR"},{"key":"2185_CR41","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., et al. (2017). The 2017 DAVIS challenge on video object segmentation. CoRR abs\/1704.00675"},{"key":"2185_CR42","first-page":"8743","volume":"45","author":"L Qi","year":"2022","unstructured":"Qi, L., Kuen, J., Wang, Y., et al. (2022). Open world entity segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 8743\u20138756.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2185_CR43","unstructured":"Radford, A., Narasimhan, K., Salimans, T., et al. (2018). Improving language understanding by generative pre-training. OpenAI"},{"issue":"8","key":"2185_CR44","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., et al. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.","journal-title":"OpenAI blog"},{"key":"2185_CR45","unstructured":"Radford, A., Kim, JW., Hallacy, C., et al. (2021). Learning transferable visual models from natural language supervision. In International Conference on machine learning, Proceedings of Machine Learning Research, PMLR, vol 139, pp 8748\u20138763"},{"key":"2185_CR46","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Kalia, A., Petrovic, V., et al. (2023). PACO: parts and attributes of common objects. In CVPR, IEEE, pp 7141\u20137151","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"2185_CR47","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021). Vision transformers for dense prediction. In Conference on computer vision and pattern Recognition, pp 12,179\u201312,188","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"2185_CR48","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et al. (2022). High-resolution image synthesis with latent diffusion models. In Conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2185_CR49","unstructured":"Shen, Q., Yang, X., & Wang, X. (2023). Anything-3d: Towards single-view anything reconstruction in the wild. arXiv preprint arXiv:2304.10261"},{"key":"2185_CR50","unstructured":"Tang, L., Xiao, H., & Li, B. (2023). Can sam segment anything? when sam meets camouflaged object detection. arXiv preprint arXiv:2304.04709"},{"key":"2185_CR51","unstructured":"Touvron, H., Lavril, T., Izacard, G., et al. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"2185_CR52","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., et al. (2023a). Images speak in images: A generalist painter for in-context visual learning. In Conference on computer vision and pattern recognition. IEEE, pp 6830\u20136839","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"2185_CR53","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., et al. (2023b). Seggpt: Towards segmenting everything in context. In International conference on computer vision. IEEE, pp 1130\u20131140","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"2185_CR54","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhang, Y., Liu, F., et al. (2020). Synthesize then compare: Detecting failures and anomalies for semantic segmentation. European conference on computer vision, Springer, pp. 145\u2013161","DOI":"10.1007\/978-3-030-58452-8_9"},{"key":"2185_CR55","doi-asserted-by":"crossref","unstructured":"Xian, Y., Choudhury, S., He, Y., et al. (2019). Semantic projection network for zero-and few-label semantic segmentation. In Conference on computer vision and pattern recognition, pp 8256\u20138265","DOI":"10.1109\/CVPR.2019.00845"},{"key":"2185_CR56","doi-asserted-by":"crossref","unstructured":"Xu, J., Mello, SD., Liu, S., et al. (2022a). Groupvit: Semantic segmentation emerges from text supervision. In Conference on computer vision and pattern recognition. IEEE, pp 18,113\u201318,123","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"2185_CR57","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., et al. (2022). A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. European conference on computer vision, Springer, pp. 736\u2013753","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"2185_CR58","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., et al. (2023). Side adapter network for open-vocabulary semantic segmentation. In Conference on Computer Vision and Pattern Recognition, pp 2945\u20132954","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"2185_CR59","unstructured":"Yang, J., Gao, M., Li, Z., et al. (2023). Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968"},{"key":"2185_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, K., & Liu, D. (2023). Customized segment anything model for medical image segmentation. arXiv preprint arXiv:2304.13785","DOI":"10.2139\/ssrn.4495221"},{"key":"2185_CR61","unstructured":"Zhang, R., Han, J., Zhou, A., et al. (2023a). Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199"},{"key":"2185_CR62","unstructured":"Zhang, R., Jiang, Z., Guo, Z., et al. (2023b). Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048"},{"key":"2185_CR63","unstructured":"Zhang, S., Roller, S., Goyal, N., et al. (2022). Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068"},{"key":"2185_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., et al. (2023). Unleashing text-to-image diffusion models for visual perception. CoRR","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"2185_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C. C., & Dai, B. (2022). Extract free dense labels from clip. European conference on computer vision, Springer, pp. 696\u2013712","DOI":"10.1007\/978-3-031-19815-1_40"},{"issue":"2","key":"2185_CR66","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TCSVT.2022.3203595","volume":"33","author":"H Zhou","year":"2023","unstructured":"Zhou, H., Chen, P., Yang, L., et al. (2023). Activation to saliency: Forming high-quality labels for unsupervised salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 743\u2013755.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2185_CR67","doi-asserted-by":"crossref","unstructured":"Zhou, H., Qiao, B., Yang, L., et al. (2023b). Texture-guided saliency distilling for unsupervised salient object detection. In Conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52729.2023.00701"},{"key":"2185_CR68","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Lei, Y., Zhang, B., et al. (2023c). Zegclip: Towards adapting clip for zero-shot semantic segmentation. In IEEE conference on computer vision and pattern recognition, pp 11,175\u201311,185","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"2185_CR69","unstructured":"Zhu, D., Chen, J., Shen, X., et al. (2023a). Minigpt-4: Enhancing vision-language understanding with advanced large language models. CoRR abs\/2304.10592"},{"key":"2185_CR70","unstructured":"Zhu, J., Chen, Z., Hao, Z., et al. (2023b). Tracking anything in high quality. arXiv preprint arXiv:2307.13974"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02185-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02185-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02185-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T06:04:39Z","timestamp":1736229879000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02185-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,16]]},"references-count":70,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2185"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02185-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,16]]},"assertion":[{"value":"16 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}