{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:49:53Z","timestamp":1777654193595,"version":"3.51.4"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729195","type":"print"},{"value":"9783031729201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72920-1_15","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:02:57Z","timestamp":1727683377000},"page":"259-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["UMG-CLIP: A Unified Multi-granularity Vision Generalist for\u00a0Open-World Understanding"],"prefix":"10.1007","author":[{"given":"Bowen","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peisen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junni","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"15_CR1","unstructured":"Barbu, A., et al.: ObjectNet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"15_CR2","unstructured":"Bucher, M., Vu, T.H., Cord, M., P\u00e9rez, P.: Zero-shot semantic segmentation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"15_CR3","unstructured":"Byeon, M., Park, B., Kim, H., Lee, S., Baek, W., Kim, S.: COYO-700 m: image-text pair dataset. https:\/\/github.com\/kakaobrain\/coyo-dataset\/ (2022)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Cai, L., Zhang, Z., Zhu, Y., Zhang, L., Li, M., Xue, X.: BigDetection: a large-scale benchmark for improved object detector pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4777\u20134787 (2022)","DOI":"10.1109\/CVPRW56347.2022.00524"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12 m: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"15_CR6","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal llm\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"issue":"10","key":"15_CR7","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","volume":"105","author":"G Cheng","year":"2017","unstructured":"Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. Proc. IEEE 105(10), 1865\u20131883 (2017)","journal-title":"Proc. IEEE"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Cho, S., et al.: Cat-SEG: cost aggregation for open-vocabulary semantic segmentation. arXiv preprint arXiv:2303.11797 (2023)","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Chou, S.H., Fan, Z., Little, J.J., Sigal, L.: Semi-supervised grounding alignment for multi-modal feature learning. In: 2022 19th Conference on Robots and Vision (CRV), pp. 48\u201357 (2022)","DOI":"10.1109\/CRV55824.2022.00015"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"15_CR12","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223. JMLR Workshop and Conference Proceedings (2011)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"15_CR15","unstructured":"Ding, Z., Wang, J., Tu, Z.: Open-vocabulary universal image segmentation with maskclip (2023)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Dong, X., et\u00a0al.: MaskClip: masked self-distillation advances contrastive language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10995\u201311005 (2023)","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"15_CR17","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: Eva-02: a visual representation for neon genesis. arXiv preprint arXiv:2303.11331 (2023)","DOI":"10.2139\/ssrn.4813567"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Eva: Exploring the limits of masked visual representation learning at scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19358\u201319369 (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"15_CR20","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: 2004 Conference on Computer Vision and Pattern Recognition Workshop, pp. 178\u2013178. IEEE (2004)"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13696, pp. 540\u2013557. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_31","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Goodfellow, I.J., Erhan, D., Carrier, P.L., Courville, A., Mirza, M., Hamner, B., Cukierski, W., Tang, Y., Thaler, D., Lee, D.H., et\u00a0al.: Challenges in representation learning: A report on three machine learning contests. In: Neural Information Processing: 20th International Conference, ICONIP 2013, Daegu, Korea, November 3-7, 2013. Proceedings, Part III 20. pp. 117\u2013124. Springer (2013)","DOI":"10.1007\/978-3-642-42051-1_16"},{"issue":"7","key":"15_CR23","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 12(7), 2217\u20132226 (2019)","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"15_CR26","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"15_CR27","unstructured":"Jie, S., Deng, Z.H.: Convolutional bypasses are better vision transformer adapters. arXiv preprint arXiv:2207.07039 (2022)"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"15_CR30","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"15_CR31","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR32","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"issue":"11","key":"15_CR33","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"15_CR34","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: International Conference on Learning Representations (2022)"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.Y.: Mask DINO: towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"15_CR36","unstructured":"Li, J., et al.: AiluRus: a scalable VIT framework for dense prediction. In: Advances in Neural Information Processing Systems (2023)"},{"key":"15_CR37","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"15_CR38","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23390\u201323400 (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. arXiv preprint arXiv:2203.16527 (2022)","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"15_CR45","unstructured":"Ma, C., Jiang, Y., Wen, X., Yuan, Z., Qi, X.: Codet: Co-occurrence guided region-word alignment for open-vocabulary object detection. arXiv preprint arXiv:2310.16667 (2023)"},{"key":"15_CR46","doi-asserted-by":"publisher","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: SLIP: self-supervision meets language-image pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13686. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_30","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"15_CR47","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)"},{"key":"15_CR48","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2text: describing images using 1 million captioned photographs. In: Advances in Neural Information Processing Systems, vol. 24 (2011)"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Qin, J., et\u00a0al.: Freeseg: Unified, universal and open-vocabulary image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19446\u201319455 (2023)","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"15_CR50","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"key":"15_CR52","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imageNet classifiers generalize to imagenet? In: International Conference on Machine Learning, pp. 5389\u20135400. PMLR (2019)"},{"key":"15_CR53","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"15_CR54","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR55","unstructured":"Schuhmann, C., et al.: Laion-400 m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323\u2013332 (2012)","DOI":"10.1016\/j.neunet.2012.02.016"},{"key":"15_CR58","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"15_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-00934-2_24","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"BS Veeling","year":"2018","unstructured":"Veeling, B.S., Linmans, J., Winkens, J., Cohen, T., Welling, M.: Rotation equivariant CNNs for digital pathology. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018, Part II. LNCS, vol. 11071, pp. 210\u2013218. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00934-2_24"},{"key":"15_CR60","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"15_CR61","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Sam-clip: merging vision foundation models towards semantic and spatial understanding. arXiv preprint arXiv:2310.15308 (2023)","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"15_CR62","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: V3det: vast vocabulary visual detection dataset. arXiv preprint arXiv:2304.03752 (2023)","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"15_CR63","unstructured":"Wang, W., et\u00a0al.: The all-seeing project: towards panoptic visual recognition and understanding of the open world. arXiv preprint arXiv:2308.01907 (2023)"},{"key":"15_CR64","doi-asserted-by":"crossref","unstructured":"Wu, X., Zhu, F., Zhao, R., Li, H.: Cora: adapting clip for open-vocabulary detection with region prompting and anchor pre-matching. ArXiv abs\/2303.13076 (2023)","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Xian, Y., Choudhury, S., He, Y., Schiele, B., Akata, Z.: Semantic projection network for zero-and few-label semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8256\u20138265 (2019)","DOI":"10.1109\/CVPR.2019.00845"},{"key":"15_CR66","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: Large-scale scene recognition from abbey to zoo. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"15_CR67","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"15_CR68","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"15_CR69","doi-asserted-by":"publisher","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13689, pp. 736\u2013753. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"15_CR70","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: Attentive mask clip. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2771\u20132781 (2023)","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"15_CR71","first-page":"9125","volume":"35","author":"L Yao","year":"2022","unstructured":"Yao, L., et al.: Detclip: dictionary-enriched visual-concept paralleled pre-training for open-world detection. Adv. Neural. Inf. Process. Syst. 35, 9125\u20139138 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR72","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"15_CR73","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Convolutions die hard: open-vocabulary segmentation with single frozen convolutional clip. arXiv preprint arXiv:2308.02487 (2023)"},{"key":"15_CR74","first-page":"36067","volume":"35","author":"H Zhang","year":"2022","unstructured":"Zhang, H., et al.: Glipv2: unifying localization and vision-language understanding. Adv. Neural. Inf. Process. Syst. 35, 36067\u201336080 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR75","unstructured":"Zhang, S., et al.: Gpt4roi: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"15_CR76","unstructured":"Zhang, Y., et\u00a0al.: Recognize anything: a strong image tagging model. arXiv preprint arXiv:2306.03514 (2023)"},{"key":"15_CR77","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72920-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:53:44Z","timestamp":1732830824000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72920-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729195","9783031729201"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72920-1_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}