{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T04:55:54Z","timestamp":1768625754382,"version":"3.49.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031207150","type":"print"},{"value":"9783031207167","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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20716-7_19","type":"book-chapter","created":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T05:03:02Z","timestamp":1670562182000},"page":"245-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GUILD - A Generator for\u00a0Usable Images in\u00a0Large-Scale Datasets"],"prefix":"10.1007","author":[{"given":"Peter","family":"Roch","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bijan","family":"Shahbaz Nejad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Handte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro Jos\u00e9","family":"Marr\u00f3n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,10]]},"reference":[{"key":"19_CR1","unstructured":"Amazon Mechanical Turk Inc: Amazon Mechanical Turk. www.mturk.com (2018). (Accessed 09 Nov 2021)"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Barz, B., Denzler, J.: Deep learning on small datasets without pre-training using cosine loss. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2020)","DOI":"10.1109\/WACV45572.2020.9093286"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Birhane, A., Prabhu, V.U.: Large image datasets: A pyrrhic win for computer vision? In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00158"},{"key":"19_CR4","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. CoRR (2020)"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Bryant, D., Howard, A.: A comparative analysis of emotion-detecting ai systems with respect to algorithm performance and dataset diversity. In: Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society (2019)","DOI":"10.1145\/3306618.3314284"},{"key":"19_CR6","unstructured":"Chang, A.X., et al.: Shapenet: An information-rich 3d model repository. CoRR (2015)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: An overview. IEEE Signal Process. Mag. (2018)","DOI":"10.1109\/MSP.2017.2765202"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"19_CR9","unstructured":"Doan, A.D., Jawaid, A.M., Do, T.T., Chin, T.J.: G2D: from GTA to data. CoRR (2018)"},{"key":"19_CR10","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: An open urban driving simulator. CoRL (2017)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: A retrospective. In: IJCV (2015)","DOI":"10.1007\/s11263-014-0733-5"},{"key":"19_CR12","unstructured":"Flickr Inc: Flickr (2021). www.flickr.com. (Accessed: 08 Nov 2021)"},{"key":"19_CR13","unstructured":"Google LLC : Open Images V6 - Description (2020). www.storage.googleapis.com\/openimages\/web\/factsfigures.html. (Accessed: 18 Jul 2022)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Doll\u00e1r, P., Girshick, R.: Lvis: A dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"19_CR15","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015)"},{"key":"19_CR16","unstructured":"Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Tech. rep, UMass Amherst (2007)"},{"key":"19_CR17","unstructured":"IAM, Universit\u00e4t Duisburg-Essen: Taxiladekonzept f\u00fcr Elektrotaxis im \u00f6ffentlichen Raum (2022). https:\/\/talako.uni-due.de. (Accessed: 14 Jan 2022)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: ICCVW (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"19_CR21","unstructured":"Kutsenko, D.: Rpg\/fps game assets for pc\/mobile (industrial set v2.0) (2021). https:\/\/assetstore.unity.com\/packages\/3d\/environments\/industrial\/rpg-fps-game-assets-for-pc-mobile-industrial-set-v2-0-86679. (Accessed: 11 Jul 2022)"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et al.: The open images dataset v4. In: IJCV (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Le, H.A., Mensink, T., Das, P., Karaoglu, S., Gevers, T.: Eden: Multimodal synthetic dataset of enclosed garden scenes. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00162"},{"key":"19_CR24","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":"19_CR25","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M.B., Vedaldi, A.: Fine-grained visual classification of aircraft. CoRR (2013)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Mousavi, M., Khanal, A., Estrada, R.: Ai playground: Unreal engine-based data ablation tool for deep learning. In: ISVC (2020)","DOI":"10.1007\/978-3-030-64559-5_41"},{"key":"19_CR27","unstructured":"Olson, M., Wyner, A., Berk, R.: Modern neural networks generalize on small data sets. In: Advances in Neural Information Processing Systems (2018)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Qiu, W., et al.: Unrealcv: Virtual worlds for computer vision. In: ACM MM (2017)","DOI":"10.1145\/3123266.3129396"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Reddy, N.D., Vo, M., Narasimhan, S.G.: Occlusion-net: 2d\/3d occluded keypoint localization using graph networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00750"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Richter, S.R., Hayder, Z., Koltun, V.: Playing for benchmarks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.243"},{"key":"19_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-46475-6_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"SR Richter","year":"2016","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102\u2013118. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7"},{"key":"19_CR33","unstructured":"Robust Vision Challenge: Robust Vision Challenge 2020 (2020). www.robustvision.net. (Accessed: 08 Nov 2021)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Roch, P., Shahbaz Nejad, B., Handte, M., Marr\u00f3n, P.J.: Car pose estimation through wheel detection. In: ISVC (2021)","DOI":"10.1007\/978-3-030-90439-5_21"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.352"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. In: IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Shah, S., Dey, D., Lovett, C., Kapoor, A.: Airsim: High-fidelity visual and physical simulation for autonomous vehicles. In: FSR (2017)","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., Guibas, L.J.: Render for cnn: Viewpoint estimation in images using cnns trained with rendered 3d model views. In: 2015 IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.308"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Tafazzoli, F., Frigui, H., Nishiyama, K.: A large and diverse dataset for improved vehicle make and model recognition. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.121"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: A large data set for nonparametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2008)","DOI":"10.1109\/TPAMI.2008.128"},{"key":"19_CR43","unstructured":"Unity Technologies: Unity. www.unity.com (2021). (Accessed 07 Dec 2021)"},{"key":"19_CR44","unstructured":"Unity Technologies: Unity Asset Store. https:\/\/assetstore.unity.com (2021). (Accessed: 07 Dec 2021)"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Csurka, G., Cabon, Y., Humenberger, M.: Visual localization by learning objects-of-interest dense match regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00578"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Wohlhart, P., Lepetit, V.: Learning descriptors for object recognition and 3d pose estimation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. In: TPAMI (2019)","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Yang, L., Luo, P., Loy, C.C., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: Wider face: A face detection benchmark. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.596"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Zakharov, E., Shysheya, A., Burkov, E., Lempitsky, V.: Few-shot adversarial learning of realistic neural talking head models. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00955"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20716-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T05:06:54Z","timestamp":1670562414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20716-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031207150","9783031207167"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20716-7_19","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":"10 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Diego, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"3 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 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":"isvc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isvc.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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"110","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":"61","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":"55% - 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":"2-3","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)"}}]}}