{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:07:00Z","timestamp":1776888420698,"version":"3.51.2"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726422","type":"print"},{"value":"9783031726439","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-72643-9_7","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T20:48:59Z","timestamp":1732222139000},"page":"106-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MarvelOVD: Marrying Object Recognition and\u00a0Vision-Language Models for\u00a0Robust Open-Vocabulary Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-4134","authenticated-orcid":false,"given":"Kuo","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lechao","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weikai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pingping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"7_CR1","first-page":"33781","volume":"35","author":"H Bangalath","year":"2022","unstructured":"Bangalath, H., Maaz, M., Khattak, M.U., Khan, S.H., Shahbaz Khan, F.: Bridging the gap between object and image-level representations for open-vocabulary detection. Adv. Neural. Inf. Process. Syst. 35, 33781\u201333794 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR2","doi-asserted-by":"publisher","unstructured":"Bravo, M.A., Mittal, S., Brox, T.: Localized vision-language matching for open-vocabulary object detection. In: Andres, B., Bernard, F., Cremers, D., Frintrop, S., Goldl\u00fccke, B., Ihrke, I. (eds.) DAGM GCPR 2022, pp. 393\u2013408. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16788-1_24","DOI":"10.1007\/978-3-031-16788-1_24"},{"key":"7_CR3","unstructured":"Chen, P., et al.: Open vocabulary object detection with proposal mining and prediction equalization. arXiv preprint arXiv:2206.11134 (2022)"},{"key":"7_CR4","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14084\u201314093 (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"7_CR5","doi-asserted-by":"publisher","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, Part IX, pp. 701\u2013717. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"7_CR6","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. Adv. Neural Inf. Process. Syst. 26 (2013)"},{"key":"7_CR7","doi-asserted-by":"publisher","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, Part X, pp. 266\u2013282. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_16","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"7_CR8","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference On Computer Vision And Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR12","unstructured":"Jayaraman, D., Grauman, K.: Zero-shot recognition with unreliable attributes. Adv. Neural Inf. Process Syst. 27 (2014)"},{"key":"7_CR13","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":"7_CR14","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"7_CR15","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":"7_CR16","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Distilling detr with visual-linguistic knowledge for open-vocabulary object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6501\u20136510 (2023)","DOI":"10.1109\/ICCV51070.2023.00598"},{"key":"7_CR18","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":"7_CR19","unstructured":"Lin, C., et al.: Learning object-language alignments for open-vocabulary object detection. arXiv preprint arXiv:2211.14843 (2022)"},{"key":"7_CR20","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":"7_CR21","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7_CR22","unstructured":"Liu, Y.C., et al.: Unbiased teacher for semi-supervised object detection. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"7_CR23","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"7_CR24","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":"7_CR25","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: Denseclip: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Shi, H., Hayat, M., Wu, Y., Cai, J.: Proposalclip: unsupervised open-category object proposal generation via exploiting clip cues. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9611\u20139620 (2022)","DOI":"10.1109\/CVPR52688.2022.00939"},{"key":"7_CR27","unstructured":"Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv. Neural. Inf. Process. Syst. 33, 596\u2013608 (2020)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Object-aware distillation pyramid for open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11186\u201311196 (2023)","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"7_CR29","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":"7_CR30","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":"7_CR31","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3060\u20133069 (2021)","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Yun, S., Park, S.H., Seo, P.H., Shin, J.: Ifseg: image-free semantic segmentation via vision-language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2967\u20132977 (2023)","DOI":"10.1109\/CVPR52729.2023.00290"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary detr with conditional matching. In: European Conference on Computer Vision, pp. 106\u2013122. Springer, Heidelberg (2022)","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Lit: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"7_CR37","unstructured":"Zhang, H., et al.: Glipv2: unifying localization and vision-language understanding. Adv. Neural. Inf. Process. Syst. 35, 36067\u201336080 (2022)"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, S., et al.: Exploiting unlabeled data with vision and language models for object detection. In: European Conference on Computer Vision, pp. 159\u2013175. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: 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"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip. In: European Conference on Computer Vision, pp. 696\u2013712. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"7_CR41","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: European Conference on Computer Vision, pp. 350\u2013368. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"7_CR42","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Probabilistic two-stage detection. arXiv preprint 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\/978-3-031-72643-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T21:24:48Z","timestamp":1732224288000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72643-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726422","9783031726439"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72643-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 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"}}]}}