{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:11:05Z","timestamp":1780765865343,"version":"3.54.1"},"publisher-location":"Cham","reference-count":78,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-72970-6_19","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:50:38Z","timestamp":1732272638000},"page":"330-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Tokenize Anything via\u00a0Prompting"],"prefix":"10.1007","author":[{"given":"Ting","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lulu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinlong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"19_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: YOLACT: real-time instance segmentation. In: ICCV, pp. 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"19_CR4","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. NeurIPS 34, 17864\u201317875 (2021)","journal-title":"NeurIPS"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: CVPR, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"19_CR6","unstructured":"Ding, Z., Wang, J., Tu, Z.: Open-vocabulary panoptic segmentation with maskclip. arXiv preprint arXiv:2208.08984 (2022)"},{"key":"19_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"19_CR8","unstructured":"Geng, X., Liu, H.: Openllama: an open reproduction of llama. URL: https:\/\/github.com\/openlm-research\/open_llama (2023)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: CVPR, pp. 2918\u20132928 (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"19_CR10","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":"19_CR11","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"19_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Huynh, D., Kuen, J., Lin, Z., Gu, J., Elhamifar, E.: Open-vocabulary instance segmentation via robust cross-modal pseudo-labeling. In: CVPR, pp. 7020\u20137031 (2022)","DOI":"10.1109\/CVPR52688.2022.00689"},{"issue":"1","key":"19_CR17","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"19_CR18","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":"19_CR19","doi-asserted-by":"crossref","unstructured":"Karazija, L., Laina, I., Vedaldi, A., Rupprecht, C.: Diffusion models for zero-shot open-vocabulary segmentation. arXiv preprint arXiv:2306.09316 (2023)","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"19_CR20","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"19_CR21","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. IJCV 123, 32\u201373 (2017)","journal-title":"IJCV"},{"key":"19_CR22","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: F-vlm: open-vocabulary object detection upon frozen vision and language models. arXiv preprint arXiv:2209.15639 (2022)"},{"issue":"7","key":"19_CR23","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. IJCV 128(7), 1956\u20131981 (2020)","journal-title":"IJCV"},{"key":"19_CR24","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation (2022)"},{"key":"19_CR25","unstructured":"Li, F., et al.: semantic-sam: Segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767 (2023)"},{"key":"19_CR26","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":"19_CR27","doi-asserted-by":"publisher","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds) Computer Vision - ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13669, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Mvitv2: improved multiscale vision transformers for classification and detection. In: CVPR, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: CVPR, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"19_CR31","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":"19_CR32","unstructured":"Liu, Z., et\u00a0al.: Internchat: solving vision-centric tasks by interacting with chatbots beyond language. arXiv preprint arXiv:2305.05662 (2023)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"19_CR34","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2017)"},{"key":"19_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"19_CR36","unstructured":"Lu, J., Clark, C., Zellers, R., Mottaghi, R., Kembhavi, A.: Unified-IO: a unified model for vision, language, and multi-modal tasks. arXiv preprint arXiv:2206.08916 (2022)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S., Net, V.: Fully convolutional neural networks for volumetric medical image segmentation. In: Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571 (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"19_CR39","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. arXiv preprint arXiv:2306.09683 (2023)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Qin, J., et\u00a0al.: Freeseg: Unified, universal and open-vocabulary image segmentation. In: CVPR, pp. 19446\u201319455 (2023)","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"19_CR41","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"19_CR42","unstructured":"Schuhmann, C., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: ICCV, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"19_CR45","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: ACL, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"issue":"1","key":"19_CR46","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"19_CR47","unstructured":"Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. arXiv preprint arXiv:2104.09864 (2021)"},{"key":"19_CR48","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":"19_CR49","unstructured":"Sun, Q., et al.: Generative pretraining in multimodality. arXiv preprint arXiv:2307.05222 (2023)"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: VRP-SAM: SAM with visual reference prompt. arXiv preprint arXiv:2402.17726 (2024)","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Alpha-clip: a clip model focusing on wherever you want. arXiv preprint arXiv:2312.03818 (2023)","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"19_CR52","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":"19_CR53","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Object-aware distillation pyramid for open-vocabulary object detection. In: CVPR, pp. 11186\u201311196 (2023)","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"19_CR54","unstructured":"Wang, T., et\u00a0al.: Caption anything: interactive image description with diverse multimodal controls. arXiv preprint arXiv:2305.02677 (2023)"},{"key":"19_CR55","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":"19_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-030-58523-5_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Wang","year":"2020","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: SOLO: segmenting objects by locations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 649\u2013665. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_38"},{"key":"19_CR57","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., Huang, T.: Images speak in images: a generalist painter for in-context visual learning. arXiv preprint arXiv:2212.02499 (2022)","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"19_CR58","first-page":"17721","volume":"33","author":"X Wang","year":"2020","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: Solov2: dynamic and fast instance segmentation. NeurIPS 33, 17721\u201317732 (2020)","journal-title":"NeurIPS"},{"key":"19_CR59","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., Huang, T.: SegGPT: towards segmenting everything in context. In: ICCV, pp. 1130\u20131140 (2023)","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"19_CR60","unstructured":"Wu, J., et al.: Grit: a generative region-to-text transformer for object understanding. arXiv preprint arXiv:2212.00280 (2022)"},{"key":"19_CR61","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Betrayed by captions: joint caption grounding and generation for open vocabulary instance segmentation. arXiv preprint arXiv:2301.00805 (2023)","DOI":"10.36227\/techrxiv.22082723.v1"},{"key":"19_CR62","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: European Conference on Computer Vision, Springer, Cham (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"19_CR63","unstructured":"Xiaoke, H., et al.: Segment and caption anything. arXiv preprint arXiv:2312.00869 (2023)"},{"key":"19_CR64","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et\u00a0al.: Efficientsam: leveraged masked image pretraining for efficient segment anything. arXiv preprint arXiv:2312.00863 (2023)","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"Xu, J., De\u00a0Mello, S., Liu, S., Byeon, W., Breuel, T., Kautz, J., Wang, X.: Groupvit: semantic segmentation emerges from text supervision. In: CVPR, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"19_CR66","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: CVPR, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"19_CR67","unstructured":"Yang, H., Ma, C., Wen, B., Jiang, Y., Yuan, Z., Zhu, X.: Recognize any regions. arXiv preprint arXiv:2311.01373 (2023)"},{"key":"19_CR68","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. NeurIPS 35, 9125\u20139138 (2022)","journal-title":"NeurIPS"},{"key":"19_CR69","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: CVPR, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"19_CR70","unstructured":"Zhang, C., et al.: Faster segment anything: towards lightweight sam for mobile applications. arXiv preprint arXiv:2306.14289 (2023)"},{"key":"19_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, F., Zou, X., Liu, S., Li, C., Yang, J., Zhang, L.: A simple framework for open-vocabulary segmentation and detection. In: ICCV, pp. 1020\u20131031 (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"19_CR72","unstructured":"Zhang, S., et al.: Gpt4roi: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"19_CR73","unstructured":"Zheng, L., et\u00a0al.: Judging llm-as-a-judge with MT-bench and chatbot arena. arXiv preprint arXiv:2306.05685 (2023)"},{"key":"19_CR74","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":"19_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"19_CR76","doi-asserted-by":"publisher","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from CLIP. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"19_CR77","doi-asserted-by":"crossref","unstructured":"Zou, X., et\u00a0al.: Generalized decoding for pixel, image, and language. In: CVPR, pp. 15116\u201315127 (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"19_CR78","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. arXiv preprint arXiv:2304.06718 (2023)"}],"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\/978-3-031-72970-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:17:47Z","timestamp":1732274267000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":78,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 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"}}]}}