{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T13:20:44Z","timestamp":1777036844363,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031167874","type":"print"},{"value":"9783031167881","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16788-1_24","type":"book-chapter","created":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T20:35:56Z","timestamp":1663878956000},"page":"393-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Localized Vision-Language Matching for Open-vocabulary Object Detection"],"prefix":"10.1007","author":[{"given":"Mar\u00eda A.","family":"Bravo","sequence":"first","affiliation":[]},{"given":"Sudhanshu","family":"Mittal","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Brox","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,20]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Amrani, E., Ben-Ari, R., Shapira, I., Hakim, T., Bronstein, A.: Self-supervised object detection and retrieval using unlabeled videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 954\u2013955 (2020)","DOI":"10.1109\/CVPRW50498.2020.00485"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 384\u2013400 (2018)","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"24_CR3","unstructured":"Bertasius, G., Torresani, L.: Cobe: contextualized object embeddings from narrated instructional video. Adv. Neural Inf. Process. Syst. 33, 15133\u201315145 (2020)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2846\u20132854 (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"24_CR5","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"24_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Yu., Liu, J.: UNITER: uNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Ma, L., Luo, W., Wong, K.Y.K.: Weakly-supervised spatio-temporally grounding natural sentence in video. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1183"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Cinbis, R.G., Verbeek, J., Schmid, C.: Weakly supervised object localization with multi-fold multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 39(1), 189\u2013203 (2017)","DOI":"10.1109\/TPAMI.2016.2535231"},{"key":"24_CR9","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 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"24_CR10","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Dong, J., Li, X., Xu, C., Ji, S., He, Y., Yang, G., Wang, X.: Dual encoding for zero-example video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9346\u20139355 (2019)","DOI":"10.1109\/CVPR.2019.00957"},{"key":"24_CR12","unstructured":"Ging, S., Zolfaghari, M., Pirsiavash, H., Brox, T.: Coot: cooperative hierarchical transformer for video-text representation learning. Adv. Neural Inf. Process. Syst. (NeurIPS), textbf33, 22605\u201322618 (2020)"},{"key":"24_CR13","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. Int. Conf. Learn. Representations (2022). https:\/\/openreview.net\/forum?id=lL3lnMbR4WU"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR15","unstructured":"Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, J.: Pixel-bert: Aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)"},{"key":"24_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. arXiv preprint arXiv:2111.12698 (2021)","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"24_CR17","unstructured":"Jeong, J., Lee, S., Kim, J., Kwak, N.: Consistency-based semi-supervised learning for object detection. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"issue":"2","key":"24_CR18","doi-asserted-by":"publisher","first-page":"5453","DOI":"10.1109\/LRA.2022.3146922","volume":"7","author":"D Kim","year":"2022","unstructured":"Kim, D., Lin, T.Y., Angelova, A., Kweon, I.S., Kuo, W.: Learning open-world object proposals without learning to classify. IEEE Robot. Autom. Lett. 7(2), 5453\u20135460 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Klein, B., Lev, G., Sadeh, G., Wolf, L.: Associating neural word embeddings with deep image representations using fisher vectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4437\u20134446 (2015)","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Kosugi, S., Yamasaki, T., Aizawa, K.: Object-aware instance labeling for weakly supervised object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6064\u20136072 (2019)","DOI":"10.1109\/ICCV.2019.00616"},{"key":"24_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"24_CR22","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":"TY 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":"24_CR23","unstructured":"Liu, Y.C., et al.: Unbiased teacher for semi-supervised object detection. In: International Conference on Learning Representations (2021)"},{"key":"24_CR24","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems, vol. 32 (2019)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Laptev, I., Sivic, J., Zisserman, A.: Thinking fast and slow: efficient text-to-visual retrieval with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9826\u20139836 (2021)","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Pham, K., Kafle, K., Lin, Z., Ding, Z., Cohen, S., Tran, Q., Shrivastava, A.: Learning to predict visual attributes in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13018\u201313028 (2021)","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"24_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Rahman, S., Khan, S., Barnes, N.: Improved visual-semantic alignment for zero-shot object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 11932\u201311939 (2020)","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"24_CR30","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: Instance-aware, context-focused, and memory-efficient weakly supervised object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10598\u201310607 (2020)","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Chen, K., Nevatia, R.: Video object grounding using semantic roles in language description. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10417\u201310427 (2020)","DOI":"10.1109\/CVPR42600.2020.01043"},{"key":"24_CR33","unstructured":"Sohn, K., Zhang, Z., Li, C., Zhang, H., Lee, C., Pfister, T.: A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020)"},{"key":"24_CR34","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J.: Vl-bert: pre-training of generic visual-linguistic representations. In: International Conference on Learning Representations (2019)"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 394\u2013407(2018)","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"24_CR37","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"},{"key":"24_CR38","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"24_CR39","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 (CVPR), pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, P., Li, X., Hu, X., Yang, J., Zhang, L., Wang, L., Choi, Y., Gao, J.: Vinvl: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhao, Z., Zhao, Y., Wang, Q., Liu, H., Gao, L.: Where does it exist: spatio-temporal video grounding for multi-form sentences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10668\u201310677 (2020)","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: Regionclip: Region-based language-image pretraining. arXiv preprint arXiv:2112.09106 (2021)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, P., Wang, H., Saligrama, V.: Don\u2019t even look once: synthesizing features for zero-shot detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11693\u201311702 (2020)","DOI":"10.1109\/CVPR42600.2020.01171"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16788-1_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T03:53:16Z","timestamp":1676865196000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16788-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031167874","9783031167881"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16788-1_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Konstanz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/gcpr-vmv-2022.uni-konstanz.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"78","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}