{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T16:57:29Z","timestamp":1783357049821,"version":"3.54.6"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","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\/978-3-031-20074-8_1","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["ECCV Caption: Correcting False Negatives by\u00a0Collecting Machine-and-Human-verified Image-Caption Associations for\u00a0MS-COCO"],"prefix":"10.1007","author":[{"given":"Sanghyuk","family":"Chun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wonjae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsuk","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seong Joon","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Uijlings, J.R., Ferrari, V.: Fluid annotation: a human-machine collaboration interface for full image annotation. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1957\u20131966 (2018)","DOI":"10.1145\/3240508.3241916"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Benenson, R., Popov, S., Ferrari, V.: Large-scale interactive object segmentation with human annotators. In: Proceedings of CVPR, pp. 11700\u201311709 (2019)","DOI":"10.1109\/CVPR.2019.01197"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Bernstein, M.S., et al.: Soylent: a word processor with a crowd inside. In: Proceedings of the 23nd Annual ACM Symposium on User Interface Software and Technology, pp. 313\u2013322 (2010)","DOI":"10.1145\/1866029.1866078"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Mafla, A., G\u00f3mez, L., Karatzas, D.: Is an image worth five sentences? a new look into semantics for image-text matching. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1391\u20131400 (2022)","DOI":"10.1109\/WACV51458.2022.00254"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Boykov, Y.Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in nd images. In: Proceedings of ICCV, vol. 1, pp. 105\u2013112. IEEE (2001)","DOI":"10.1109\/ICCV.2001.937505"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika 39(3\/4), 324\u2013345 (1952)","DOI":"10.1093\/biomet\/39.3-4.324"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Cer, D., et al.: Universal sentence encoder. In: Proceedings of EMNLP (2018)","DOI":"10.18653\/v1\/D18-2029"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Chang, M., Guillain, L.V., Jung, H., Hare, V.M., Kim, J., Agrawala, M.: Recipescape: an interactive tool for analyzing cooking instructions at scale. In: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pp. 1\u201312 (2018)","DOI":"10.1145\/3173574.3174025"},{"key":"1_CR10","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: Proceedings of CVPR, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, H., Wu, H., Jiang, Y., Wang, C.: Learning the best pooling strategy for visual semantic embedding. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"1_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-030-58601-0_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Chen","year":"2020","unstructured":"Chen, T., Deng, J., Luo, J.: Adaptive offline quintuplet loss for image-text matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 549\u2013565. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_33"},{"key":"1_CR13","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Chun, S., Oh, S.J., De Rezende, R.S., Kalantidis, Y., Larlus, D.: Probabilistic embeddings for cross-modal retrieval. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"1_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3359164","volume":"3","author":"JJY Chung","year":"2019","unstructured":"Chung, J.J.Y., Song, J.Y., Kutty, S., Hong, S., Kim, J., Lasecki, W.S.: Efficient elicitation approaches to estimate collective crowd answers. Proc. ACM Hum.-Comput. Interact. 3, 1\u201325 (2019)","journal-title":"Proc. ACM Hum.-Comput. Interact."},{"key":"1_CR17","unstructured":"Desai, K., Kaul, G., Aysola, Z., Johnson, J.: RedCaps: web-curated image-text data created by the people, for the people. In: NeurIPS Datasets and Benchmarks (2021)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. In: Proceedings of AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"1_CR19","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: Proceedinngs of ICLR (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"1_CR20","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: Improving visual-semantic embeddings with hard negatives. In: Proceedings of BMVC (2018)"},{"key":"1_CR21","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Proceedings of NeurIPS, pp. 2121\u20132129 (2013)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Joty, S.R., Niu, L., Wang, G.: Look, imagine and match: improving textual-visual cross-modal retrieval with generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7181\u20137189 (2018)","DOI":"10.1109\/CVPR.2018.00750"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Guo, A., et al.: Vizlens: a robust and interactive screen reader for interfaces in the real world. Proceedings of the 29th Annual Symposium on User Interface Software and Technology (2016)","DOI":"10.1145\/2984511.2984518"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C., Wang, L.: Learning semantic concepts and order for image and sentence matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6163\u20136171 (2018)","DOI":"10.1109\/CVPR.2018.00645"},{"key":"1_CR26","unstructured":"Huang, Z., et al.: Learning with noisy correspondence for cross-modal matching. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Proceedings of NeurIPS (2021). https:\/\/openreview.net\/forum?id=S9ZyhWC17wJ"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Ipeirotis, P.G., Provost, F., Wang, J.: Quality management on amazon mechanical turk. In: Proceedings of the ACM SIGKDD Workshop on Human Computation, pp. 64\u201367 (2010)","DOI":"10.1145\/1837885.1837906"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Kaplan, T., Saito, S., Hara, K., Bigham, J.P.: Striving to earn more: a survey of work strategies and tool use among crowd workers. In: HCOMP (2018)","DOI":"10.1609\/hcomp.v6i1.13327"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of CVPR, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"1\/2","key":"1_CR30","doi-asserted-by":"publisher","first-page":"81","DOI":"10.2307\/2332226","volume":"30","author":"MG Kendall","year":"1938","unstructured":"Kendall, M.G.: A new measure of rank correlation. Biometrika 30(1\/2), 81\u201393 (1938)","journal-title":"Biometrika"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Kim, J., Nguyen, P., Weir, S.A., Guo, P.J., Miller, R., Gajos, K.Z.: Crowdsourcing step-by-step information extraction to enhance existing how-to videos. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (2014)","DOI":"10.1145\/2556288.2556986"},{"key":"1_CR32","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: Proceedings of ICML (2021)"},{"key":"1_CR33","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of CVPR Worshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"1","key":"1_CR35","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(1), 32\u201373 (2017)","journal-title":"IJCV"},{"issue":"7","key":"1_CR36","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. IJCV 128(7), 1956\u20131981 (2020)","journal-title":"IJCV"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"1_CR38","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation (2022)"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: Proceedings of ICCV, pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"1_CR40","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":"1_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of CVPR, pp. 1096\u20131104 (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Mahajan, D.K., et al.: Exploring the limits of weakly supervised pretraining. In: Proceedings of ECCV (2018)","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"1_CR43","doi-asserted-by":"publisher","unstructured":"Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. 54(6) (2021). https:\/\/doi.org\/10.1145\/3457607","DOI":"10.1145\/3457607"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Musgrave, K., Belongie, S., Lim, S.N.: A metric learning reality check. In: Proceedings of ECCV (2020)","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Nushi, B., Kamar, E., Horvitz, E.: Towards accountable ai: Hybrid human-machine analyses for characterizing system failure. In: HCOMP (2018)","DOI":"10.1609\/hcomp.v6i1.13337"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Oh Song, H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Proceedings of CVPR, pp. 4004\u20134012 (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Parekh, Z., Baldridge, J., Cer, D., Waters, A., Yang, Y.: Crisscrossed captions: extended intramodal and intermodal semantic similarity judgments for ms-coco. arXiv preprint arXiv:2004.15020 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.249"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"1_CR49","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"1_CR50","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of ICML. Proceedings of Machine Learning Research, 18\u201324 July 2021, vol. 139, pp. 8748\u20138763. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"issue":"8","key":"1_CR51","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":"1_CR52","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Proceedings of NeurIPS, pp. 91\u201399 (2015)"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"1_CR54","unstructured":"Scimeca, L., Oh, S.J., Chun, S., Poli, M., Yun, S.: Which shortcut cues will dnns choose? a study from the parameter-space perspective. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"1_CR55","unstructured":"Settles, B.: Active learning literature survey (2009)"},{"key":"1_CR56","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"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Snow, R., O\u2019Connor, B., Jurafsky, D., Ng, A.: Cheap and fast - but is it good? evaluating non-expert annotations for natural language tasks. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 254\u2013263. Association for Computational Linguistics, Honolulu (2008). https:\/\/aclanthology.org\/D08-1027","DOI":"10.3115\/1613715.1613751"},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Song, J.Y., Fok, R., Lundgard, A., Yang, F., Kim, J., Lasecki, W.S.: Two tools are better than one: tool diversity as a means of improving aggregate crowd performance. In: 23rd International Conference on Intelligent User Interfaces (2018)","DOI":"10.1145\/3172944.3172948"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: Proceedings of CVPR, pp. 1979\u20131988 (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"key":"1_CR60","doi-asserted-by":"publisher","unstructured":"Sorokin, A., Forsyth, D.: Utility data annotation with amazon mechanical turk. In: 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 1\u20138 (2008). https:\/\/doi.org\/10.1109\/CVPRW.2008.4562953","DOI":"10.1109\/CVPRW.2008.4562953"},{"key":"1_CR61","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of NeurIPS, pp. 5998\u20136008 (2017)"},{"issue":"1","key":"1_CR62","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/s11263-016-0927-0","volume":"121","author":"Y Verma","year":"2017","unstructured":"Verma, Y., Jawahar, C.: Image annotation by propagating labels from semantic neighbourhoods. IJCV 121(1), 126\u2013148 (2017)","journal-title":"IJCV"},{"key":"1_CR63","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, Y., Ji, Z., Pang, Y., Ma, L.: Consensus-aware visual-semantic embedding for image-text matching. In: Proceedings of ECCV (2020)","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Wehrmann, J., Souza, D.M., Lopes, M.A., Barros, R.C.: Language-agnostic visual-semantic embeddings. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5804\u20135813 (2019)","DOI":"10.1109\/ICCV.2019.00590"},{"key":"1_CR66","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Unified visual-semantic embeddings: bridging vision and language with structured meaning representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6609\u20136618 (2019)","DOI":"10.1109\/CVPR.2019.00677"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Wu, W., Yang, J.: Smartlabel: an object labeling tool using iterated harmonic energy minimization. In: Proceedings of the 14th ACM International Conference on Multimedia, pp. 891\u2013900 (2006)","DOI":"10.1145\/1180639.1180839"},{"key":"1_CR68","doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B., Cohen, S., Yang, J., Huang, T.S.: Deep interactive object selection. In: Proceedings of CVPR, pp. 373\u2013381 (2016)","DOI":"10.1109\/CVPR.2016.47"},{"key":"1_CR69","first-page":"67","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. ACL 2, 67\u201378 (2014)","journal-title":"ACL"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Vinvl: making visual representations matter in vision-language models. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00553"}],"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\/978-3-031-20074-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:52:16Z","timestamp":1728348736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_1","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":"12 November 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)"}}]}}