{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:01:37Z","timestamp":1777568497695,"version":"3.51.4"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730009","type":"print"},{"value":"9783031730016","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-73001-6_15","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T10:24:13Z","timestamp":1732616653000},"page":"255-273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["CLIFF: Continual Latent Diffusion for\u00a0Open-Vocabulary Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7338-9251","authenticated-orcid":false,"given":"Wuyang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5180-6958","authenticated-orcid":false,"given":"Xinyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3264-3265","authenticated-orcid":false,"given":"Jiayi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0853-6948","authenticated-orcid":false,"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Ali, S., et al.: Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge. Sci. Rep. (2024)","DOI":"10.1038\/s41598-024-52063-x"},{"key":"15_CR2","unstructured":"Amit, T., Nachmani, E., Shaharbany, T., Wolf, L.: Segdiff: image segmentation with diffusion probabilistic models. ArXiv:2112.00390 (2021)"},{"key":"15_CR3","unstructured":"Bansal, A., et al.: Cold diffusion: inverting arbitrary image transforms without noise. ArXiv:2208.09392 (2022)"},{"key":"15_CR4","unstructured":"Baranchuk, D., Voynov, A., Rubachev, I., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. In: ICLR (2022)"},{"key":"15_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"15_CR6","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: diffusion model for object detection. ArXiv:2211.09788 (2022)"},{"key":"15_CR7","first-page":"102976","volume":"90","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Li, W., Xing, X., Yuan, Y.: Medical federated learning with joint graph purification for noisy label learning. Media 90, 102976 (2023)","journal-title":"Media"},{"key":"15_CR8","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.: Learning to prompt for open-vocabulary object detection with vision-language model. ArXiv:2203.14940 (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"15_CR10","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.: The pascal visual object classes (VOC) challenge. IJCV 88, 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"15_CR11","unstructured":"Feng, C., et al.: Promptdet: expand your detector vocabulary with uncurated images. ArXiv:2203.16513 (2022)"},{"key":"15_CR12","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/978-3-031-20077-9_41","volume-title":"ECCV 2022","author":"C Feng","year":"2022","unstructured":"Feng, C., et al.: PromptDet: towards open-vocabulary detection using uncurated images. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 701\u2013717. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41"},{"key":"15_CR13","unstructured":"Gao, M., et al.: Towards open vocabulary object detection without human-provided bounding boxes. ArXiv:2111.09452 (2021)"},{"key":"15_CR14","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1007\/978-3-031-20080-9_16","volume-title":"ECCV 2022","author":"M Gao","year":"2022","unstructured":"Gao, M., et al.: Open vocabulary object detection with pseudo bounding-box labels. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 266\u2013282. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_16"},{"key":"15_CR15","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: ICLR (2022)"},{"key":"15_CR16","unstructured":"Gu, Z., Chen, H., Xu, Z., Lan, J., Meng, C., Wang, W.: Diffusioninst: diffusion model for instance segmentation. ArXiv:2212.02773 (2022)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Han, J., Ren, Y., Ding, J., Yan, K., Xia, G.S.: Few-shot object detection via variational feature aggregation. ArXiv:2301.13411 (2023)","DOI":"10.1609\/aaai.v37i1.25153"},{"key":"15_CR19","unstructured":"Han, X., Zheng, H., Zhou, M.: Card: classification and regression diffusion models. In: NeurIPS (2022)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"15_CR21","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Contrastive feature masking open-vocabulary vision transformer. In: ICCV, pp. 15602\u201315612 (2023)","DOI":"10.1109\/ICCV51070.2023.01430"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Region-aware pretraining for open-vocabulary object detection with vision transformers. In: CVPR, pp. 11144\u201311154 (2023)","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"15_CR24","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. ArXiv:1312.6114 (2013)"},{"key":"15_CR25","volume-title":"Combinatorial Optimization","author":"BH Korte","year":"2011","unstructured":"Korte, B.H., Vygen, J., Korte, B., Vygen, J.: Combinatorial Optimization, vol. 1. Springer, Cham (2011)"},{"key":"15_CR26","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: Open-vocabulary object detection upon frozen vision and language models. In: ICLR (2023)"},{"key":"15_CR27","unstructured":"Kwon, M., Jeong, J., Uh, Y.: Diffusion models already have a semantic latent space. In: ICLR (2023)"},{"key":"15_CR28","unstructured":"Leng, Y., et\u00a0al.: BinauralGrad: a two-stage conditional diffusion probabilistic model for binaural audio synthesis. ArXiv:2205.14807 (2022)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Li, A.C., Prabhudesai, M., Duggal, S., Brown, E., Pathak, D.: Your diffusion model is secretly a zero-shot classifier. ArXiv:2303.16203 (2023)","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Li, C., Feng, B.Y., Fan, Z., Pan, P., Wang, Z.: Steganerf: embedding invisible information within neural radiance fields. In: ICCV, pp. 441\u2013453 (2023)","DOI":"10.1109\/ICCV51070.2023.00047"},{"key":"15_CR31","doi-asserted-by":"publisher","first-page":"105144","DOI":"10.1016\/j.compbiomed.2021.105144","volume":"141","author":"C Li","year":"2022","unstructured":"Li, C., et al.: Domain generalization on medical imaging classification using episodic training with task augmentation. Comput. Biol. Med. 141, 105144 (2022)","journal-title":"Comput. Biol. Med."},{"key":"15_CR32","unstructured":"Li, C., et al.: GaussianStego: a generalizable stenography pipeline for generative 3d gaussians splatting. ArXiv:2407.01301 (2024)"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Endora: video generation models as endoscopy simulators. ArXiv:2403.11050 (2024)","DOI":"10.1007\/978-3-031-72089-5_22"},{"key":"15_CR34","unstructured":"Li, C., Liu, X., Li, W., Wang, C., Liu, H., Yuan, Y.: U-KAN makes strong backbone for medical image segmentation and generation. ArXiv:2406.02918 (2024)"},{"key":"15_CR35","unstructured":"Li, C., Zhang, Y., Li, J., Huang, Y., Ding, X.: Unsupervised anomaly segmentation using image-semantic cycle translation. ArXiv:2103.09094 (2021)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, Y., Liang, Z., Ma, W., Huang, Y., Ding, X.: Consistent posterior distributions under vessel-mixing: a regularization for cross-domain retinal artery\/vein classification. In: ICIP, pp. 61\u201365 (2021)","DOI":"10.1109\/ICIP42928.2021.9506148"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Li, W., Chen, Z., Li, B., Zhang, D., Yuan, Y.: HTD: heterogeneous task decoupling for two-stage object detection. TIP (2021)","DOI":"10.1109\/TIP.2021.3126423"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Li, W., Guo, X., Yuan, Y.: Novel scenes & classes: towards adaptive open-set object detection. In: ICCV, pp. 15780\u201315790 (2023)","DOI":"10.1109\/ICCV51070.2023.01446"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, J., Han, B., Yuan, Y.: Adjustment and alignment for unbiased open set domain adaptation. In: CVPR, pp. 24110\u201324119 (2023)","DOI":"10.1109\/CVPR52729.2023.02309"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, X., Yao, X., Yuan, Y.: Scan: Cross domain object detection with semantic conditioned adaptation. In: AAAI, pp. 1421\u20131428 (2022)","DOI":"10.1609\/aaai.v36i2.20031"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, X., Yuan, Y.: Scan++: Enhanced semantic conditioned adaptation for domain adaptive object detection. TMM (2022)","DOI":"10.1109\/TMM.2022.3217388"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, X., Yuan, Y.: Sigma: semantic-complete graph matching for domain adaptive object detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00522"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, X., Yuan, Y.: Sigma++: improved semantic-complete graph matching for domain adaptive object detection. TPAMI (2023)","DOI":"10.1109\/TPAMI.2023.3235367"},{"key":"15_CR44","unstructured":"Li, W., Yang, C., Liu, J., Liu, X., Guo, X., Yuan, Y.: Joint polyp detection and segmentation with heterogeneous endoscopic data. In: ISBI Workshop: EndoCV 2021, pp. 69\u201379. CEUR-WS Team (2021)"},{"key":"15_CR45","unstructured":"Liang, C., Wang, W., Miao, J., Yang, Y.: GMMSeg: gaussian mixture based generative semantic segmentation models. ArXiv:2210.02025 (2022)"},{"key":"15_CR46","unstructured":"Lin, C., et al.: Learning object-language alignments for open-vocabulary object detection. In: ICLR (2023)"},{"key":"15_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"15_CR48","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: ICLR (2023)"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, Y., Li, C., Li, W., Yuan, Y.: LGS: a light-weight 4D gaussian splatting for efficient surgical scene reconstruction. ArXiv:2406.16073 (2024)","DOI":"10.1007\/978-3-031-72384-1_62"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Stereo vision meta-lens-assisted driving vision. ACS Photonics (2024)","DOI":"10.1021\/acsphotonics.3c01594"},{"key":"15_CR51","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. ArXiv:2209.03003 (2022)"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, W., Yang, Q., Li, B., Yuan, Y.: Towards robust adaptive object detection under noisy annotations. In: CVPR, pp. 14207\u201314216 (2022)","DOI":"10.1109\/CVPR52688.2022.01381"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, W., Yuan, Y.: Decoupled unbiased teacher for source-free domain adaptive medical object detection. TNNLS (2023)","DOI":"10.1109\/TNNLS.2023.3272389"},{"key":"15_CR54","unstructured":"Liu, Y., Li, C., Yang, C., Yuan, Y.: EndoGaussian: Gaussian splatting for deformable surgical scene reconstruction. ArXiv:2401.12561 (2024)"},{"key":"15_CR55","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models. ArXiv:2211.01095 (2022)"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: Semantic-conditional diffusion networks for image captioning. ArXiv:2212.03099 (2022)","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"15_CR57","unstructured":"Ma, C., Jiang, Y., Wen, X., Yuan, Z., Qi, X.: CoDet: co-occurrence guided region-word alignment for open-vocabulary object detection. NeurIPS 36 (2024)"},{"key":"15_CR58","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/978-3-031-20080-9_30","volume-title":"ECCV 2022","author":"M Maaz","year":"2022","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S., Anwer, R.M., Yang, M.H.: Class-agnostic object detection with multi-modal transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 512\u2013531. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_30"},{"issue":"1","key":"15_CR59","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1109\/LRA.2021.3123374","volume":"7","author":"D Miller","year":"2021","unstructured":"Miller, D., S\u00fcnderhauf, N., Milford, M., Dayoub, F.: Uncertainty for identifying open-set errors in visual object detection. Robot. Autom. Lett. 7(1), 215\u2013222 (2021)","journal-title":"Robot. Autom. Lett."},{"key":"15_CR60","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"ECCV 2022","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"key":"15_CR61","doi-asserted-by":"crossref","unstructured":"Ni, J., Qiu, Q., Chellappa, R.: Subspace interpolation via dictionary learning for unsupervised domain adaptation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.95"},{"key":"15_CR62","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML (2021)"},{"key":"15_CR63","unstructured":"Norris, J.R.: Markov Chains. No.\u00a02, Cambridge University Press, Cambridge (1998)"},{"key":"15_CR64","doi-asserted-by":"crossref","unstructured":"Pan, P., Fan, Z., Feng, B.Y., Wang, P., Li, C., Wang, Z.: Learning to estimate 6dof pose from limited data: A few-shot, generalizable approach using RGB images. In: 2024 International Conference on 3D Vision (3DV), pp. 1059\u20131071. IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00078"},{"key":"15_CR65","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. ArXiv:2212.09748 (2022)"},{"key":"15_CR66","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: CVPR, pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"15_CR67","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"15_CR68","unstructured":"Rasheed, H.A., Maaz, M., Khattak, M.U., Khan, S., Khan, F.: Bridging the gap between object and image-level representations for open-vocabulary detection. In: NeurIPS (2022)"},{"key":"15_CR69","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"15_CR70","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR71","doi-asserted-by":"crossref","unstructured":"Shi, C., Yang, S.: EdaDet: open-vocabulary object detection using early dense alignment. In: ICCV, pp. 15724\u201315734 (2023)","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"15_CR72","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Open-vocabulary object detection with an open corpus. In: ICCV, pp. 6759\u20136769 (2023)","DOI":"10.1109\/ICCV51070.2023.00622"},{"key":"15_CR73","unstructured":"Wizadwongsa, S., Suwajanakorn, S.: Accelerating guided diffusion sampling with splitting numerical methods. In: ICLR (2023)"},{"key":"15_CR74","unstructured":"Wu, L., Gong, C., Liu, X., Ye, M., Liu, Q.: Diffusion-based molecule generation with informative prior bridges. ArXiv:2209.00865 (2022)"},{"key":"15_CR75","doi-asserted-by":"crossref","unstructured":"Wu, S., Zhang, W., Jin, S., Liu, W., Loy, C.C.: Aligning bag of regions for open-vocabulary object detection. ArXiv:2302.13996 (2023)","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"15_CR76","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:2303.13076 (2023)","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"15_CR77","unstructured":"Xu, H., Zhang, Y., Sun, L., Li, C., Huang, Y., Ding, X.: AFSC: Adaptive Fourier space compression for anomaly detection. ArXiv:2204.07963 (2022)"},{"key":"15_CR78","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. ArXiv:2303.04803 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"15_CR79","doi-asserted-by":"crossref","unstructured":"Yang, Q., Li, W., Li, B., Yuan, Y.: MRM: masked relation modeling for medical image pre-training with genetics. In: ICCV, pp. 21452\u201321462 (2023)","DOI":"10.1109\/ICCV51070.2023.01961"},{"key":"15_CR80","doi-asserted-by":"crossref","unstructured":"Ye, K., Zhang, M., Kovashka, A., Li, W., Qin, D., Berent, J.: Cap2det: learning to amplify weak caption supervision for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00978"},{"key":"15_CR81","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-031-20077-9_7","volume-title":"ECCV 2022","author":"Y Zang","year":"2022","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 106\u2013122. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_7"},{"key":"15_CR82","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"15_CR83","doi-asserted-by":"crossref","unstructured":"Zbinden, L., Doorenbos, L., Pissas, T., Huber, A.T., Sznitman, R., M\u00e1rquez-Neila, P.: Stochastic segmentation with conditional categorical diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00109"},{"key":"15_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/978-3-030-87231-1_15","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., et al.: Generator versus segmentor: pseudo-healthy synthesis. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12906, pp. 150\u2013160. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87231-1_15"},{"key":"15_CR85","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: Regionclip: region-based language-image pretraining. In: CVPR, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"15_CR86","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-031-20077-9_21","volume-title":"ECCV 2022","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21"},{"key":"15_CR87","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Probabilistic two-stage detection. In: ArXiv:2103.07461 (2021)"}],"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\/978-3-031-73001-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T11:11:15Z","timestamp":1732619475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73001-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031730009","9783031730016"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73001-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 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"}}]}}