{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:20:01Z","timestamp":1778080801689,"version":"3.51.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730351","type":"print"},{"value":"9783031730368","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73036-8_10","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:02:46Z","timestamp":1732093366000},"page":"162-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Region-Centric Image-Language Pretraining for\u00a0Open-Vocabulary Detection"],"prefix":"10.1007","author":[{"given":"Dahun","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anelia","family":"Angelova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weicheng","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Bai, Y., Chen, X., Kirillov, A., Yuille, A., Berg, A.C.: Point-level region contrast for object detection pre-training. In: CVPR, pp. 16061\u201316070 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01559"},{"key":"10_CR2","unstructured":"Chen, J., et al.: Exploring open-vocabulary semantic segmentation without human labels. arXiv preprint arXiv:2306.00450 (2023)"},{"key":"10_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)"},{"key":"10_CR4","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"10_CR5","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. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Feng, C., Zhong, Y., Jie, Z., Chu, X., Ren, H., Wei, X., Xie, W., Ma, L.: Promptdet: towards open-vocabulary detection using uncurated images. In: European Conference on Computer Vision, pp. 701\u2013717. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"10_CR7","unstructured":"Gadre, S.Y., et\u00a0al.: Datacomp: In search of the next generation of multimodal datasets. arXiv preprint arXiv:2304.14108 (2023)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Gao, M., Xing, C., Niebles, J.C., Li, J., Xu, R., Liu, W., Xiong, C.: Open vocabulary object detection with pseudo bounding-box labels. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"10_CR9","unstructured":"Grauman, K., et\u00a0al.: Ego4d: Around the world in 3,000 hours of egocentric video. In: CVPR, pp. 18995\u201319012 (2022)"},{"key":"10_CR10","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: ICLR (2022)"},{"key":"10_CR11","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"10_CR13","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7020\u20137031 (2022)","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"10_CR14","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"10_CR15","unstructured":"Kaul, P., Xie, W., Zisserman, A.: Multi-modal classifiers for open-vocabulary object detection. arXiv preprint arXiv:2306.05493 (2023)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Contrastive feature masking open-vocabulary vision transformer. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01430"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Region-aware pretraining for open-vocabulary object detection with vision transformers. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"10_CR18","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: F-vlm: open-vocabulary object detection upon frozen vision and language models. In: ICLR (2023)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10_CR24","unstructured":"Ma, C., Jiang, Y., Wen, X., Yuan, Z., Qi, X.: Codet: co-occurrence guided region-word alignment for open-vocabulary object detection. Adv. Neural Inform. Process. Syst. 36 (2024)"},{"key":"10_CR25","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. Adv. Neural Inform. Process. Syst. 36 (2023)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection with vision transformers. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"10_CR27","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"10_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"10_CR29","unstructured":"Rasheed, H., Maaz, M., Khattak, M.U., Khan, S., Khan, F.S.: Bridging the gap between object and image-level representations for open-vocabulary detection. arXiv preprint arXiv:2207.03482 (2022)"},{"key":"10_CR30","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"10_CR31","unstructured":"Schuhmann, C., et al.: Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Shi, C., Yang, S.: Edadet: open-vocabulary object detection using early dense alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15724\u201315734 (2023)","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Object-aware distillation pyramid for open-vocabulary object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"10_CR34","unstructured":"Wei, F., Gao, Y., Wu, Z., Hu, H., Lin, S.: Aligning pretraining for detection via object-level contrastive learning. In: NeurIPS (2021)"},{"key":"10_CR35","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15254\u201315264 (2023)","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"10_CR36","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7031\u20137040 (2023)","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, T., Reed, C.J., Wang, X., Keutzer, K., Darrell, T.: Region similarity representation learning. In: ICCV, pp. 10539\u201310548 (October 2021)","DOI":"10.1109\/ICCV48922.2021.01037"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Detclipv2: scalable open-vocabulary object detection pre-training via word-region alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23497\u201323506 (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"10_CR39","unstructured":"Yao, L., et al.: Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. In: arXiv:2209.09407 (2022)"},{"key":"10_CR40","doi-asserted-by":"publisher","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching. In: ECCV. pp. 106\u2013122. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_7","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"10_CR41","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":"10_CR42","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":"10_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, S., et\u00a0al.: Exploiting unlabeled data with vision and language models for object detection. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: Regionclip: region-based language-image pretraining. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Wang, J., Wang, L., Peng, J., Wang, Y.X., Zhang, L.: Dap: detection-aware pre-training with weak supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4537\u20134546 (2021)","DOI":"10.1109\/CVPR46437.2021.00451"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_21"}],"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\/978-3-031-73036-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T16:16:58Z","timestamp":1733069818000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73036-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730351","9783031730368"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73036-8_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 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"}}]}}