{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:54:47Z","timestamp":1775325287422,"version":"3.50.1"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200588","type":"print"},{"value":"9783031200595","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\/978-3-031-20059-5_2","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"22-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Generative Negative Text Replay for\u00a0Continual Vision-Language Pretraining"],"prefix":"10.1007","author":[{"given":"Shipeng","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanqing","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinne","family":"Tuytelaars","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuming","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"2_CR1","unstructured":"Aljundi, R., et al.: Online continual learning with maximal interfered retrieval. In: NeurIPS"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"2_CR3","unstructured":"Ash, J., Adams, R.P.: On warm-starting neural network training. In: NeurIPS (2020)"},{"key":"2_CR4","unstructured":"Bao, H., Dong, L., Wei, F.: Beit: bert pre-training of image transformers. arXiv:2106.08254 (2021)"},{"key":"2_CR5","unstructured":"Barriuso, A., Torralba, A.: Notes on image annotation. arXiv:1210.3448 (2012)"},{"key":"2_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Castro, F.M., Mar\u00edn-Jim\u00e9nez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Cha, H., Lee, J., Shin, J.: Co2l: contrastive continual learning. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.00938"},{"key":"2_CR9","unstructured":"Chaudhry, A., et al.: On tiny episodic memories in continual learning. arXiv:1902.10486 (2019)"},{"key":"2_CR10","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":"2_CR11","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. arXiv:2102.02779 (2021)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.461"},{"issue":"7","key":"2_CR13","first-page":"3366","volume":"44","author":"M Delange","year":"2021","unstructured":"Delange, M., et al.: A continual learning survey: defying forgetting in classification tasks. TPAMI 44(7), 3366\u20133385 (2021)","journal-title":"TPAMI"},{"key":"2_CR14","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":"2_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-58565-5_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Douillard","year":"2020","unstructured":"Douillard, A., Cord, M., Ollion, C., Robert, T., Valle, E.: PODNet: pooled outputs distillation for small-tasks incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 86\u2013102. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_6"},{"key":"2_CR16","unstructured":"Ebrahimi, S., Elhoseiny, M., Darrell, T., Rohrbach, M.: Uncertainty-guided continual learning with bayesian neural networks. In: ICLR (2019)"},{"issue":"4","key":"2_CR17","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","volume":"28","author":"L Fei-Fei","year":"2006","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. TPAMI 28(4), 594\u2013611 (2006)","journal-title":"TPAMI"},{"key":"2_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2012.09.017","volume":"37","author":"S Grossberg","year":"2013","unstructured":"Grossberg, S.: Adaptive resonance theory: how a brain learns to consciously attend, learn, and recognize a changing world. Neural Netw. 37, 1\u201347 (2013)","journal-title":"Neural Netw."},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Han, Z., Fu, Z., Chen, S., Yang, J.: Contrastive embedding for generalized zero-shot learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incrementally via rebalancing. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00092"},{"key":"2_CR22","unstructured":"Hu, D., et al.: How well self-supervised pre-training performs with streaming data? In: ICLR (2022)"},{"key":"2_CR23","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. arXiv:2102.05918 (2021)"},{"key":"2_CR24","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: ICML (2021)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. In: Proceedings of the National Academy of Sciences (PNAS) (2017)","DOI":"10.1073\/pnas.1611835114"},{"key":"2_CR26","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report (2009)"},{"key":"2_CR27","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S., Xiong, C., Hoi, S.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS (2021)"},{"issue":"12","key":"2_CR28","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. TPAMI 40(12), 2935\u20132947 (2017)","journal-title":"TPAMI"},{"key":"2_CR29","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":"2_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Y., Schiele, B., Sun, Q.: Meta-aggregating networks for class-incremental learning. arXiv:2010.05063 (2020)","DOI":"10.1109\/CVPR46437.2021.00257"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wu, C., Tseng, S.Y., Lal, V., He, X., Duan, N.: Kd-vlp: improving end-to-end vision-and-language pretraining with object knowledge distillation. arXiv preprint. arXiv:2109.10504 (2021)","DOI":"10.18653\/v1\/2022.findings-naacl.119"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Computer Graphics and Image Processing (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: IJCV (2017)","DOI":"10.1007\/s11263-016-0965-7"},{"key":"2_CR34","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"issue":"8","key":"2_CR35","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"2_CR36","unstructured":"Rao, D., Visin, F., Rusu, A., Pascanu, R., Teh, Y.W., Hadsell, R.: Continual unsupervised representation learning. In: NeurIPS (2019)"},{"key":"2_CR37","unstructured":"Robinson, J.D., Chuang, C.Y., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. In: ICLR (2021)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"2_CR39","unstructured":"Serra, J., Suris, D., Miron, M., Karatzoglou, A.: Overcoming catastrophic forgetting with hard attention to the task. In: ICML (2018)"},{"key":"2_CR40","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 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., Harandi, M.: On learning the geodesic path for incremental learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00164"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Smith, J., Hsu, Y.C., Balloch, J., Shen, Y., Jin, H., Kira, Z.: Always be dreaming: a new approach for data-free class-incremental learning. arXiv:2106.09701 (2021)","DOI":"10.1109\/ICCV48922.2021.00924"},{"key":"2_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_8","volume-title":"Learning to Learn","author":"S Thrun","year":"1998","unstructured":"Thrun, S.: Lifelong learning algorithms. In: Pratt, L. (ed.) Learning to Learn. Springer, Boston (1998). https:\/\/doi.org\/10.1007\/978-1-4615-5529-2_8"},{"key":"2_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Wang, L., Yang, K., Li, C., Hong, L., Li, Z., Zhu, J.: OrdisCo: effective and efficient usage of incremental unlabeled data for semi-supervised continual learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00534"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: CNN-generated images are surprisingly easy to spot... for now. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Large scale incremental learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00046"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Xie, J., Yan, S., He, X.: General incremental learning with domain-aware categorical representations. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01395"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Yan, S., Xie, J., He, X.: DER: dynamically expandable representation for class incremental learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Yan, S., Zhou, J., Xie, J., Zhang, S., He, X.: An em framework for online incremental learning of semantic segmentation. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475443"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Yin, H., et al.: Dreaming to distill: data-free knowledge transfer via deepinversion. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.T.: Maintaining discrimination and fairness in class incremental learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qin, X., Su, S., Fu, Y., Lin, Z., Li, X.: When video classification meets incremental classes. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475265"},{"key":"2_CR54","unstructured":"Zhao, H., Wang, H., Fu, Y., Wu, F., Li, X.: Memory efficient class-incremental learning for image classification. In: TNNLS (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20059-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:04:45Z","timestamp":1666973085000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_2","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":"29 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}