{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T21:38:24Z","timestamp":1771018704288,"version":"3.50.1"},"reference-count":115,"publisher":"Springer Science and Business Media LLC","issue":"10-11","license":[{"start":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T00:00:00Z","timestamp":1596931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T00:00:00Z","timestamp":1596931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1514118"],"award-info":[{"award-number":["IIS-1514118"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-15-1-2291"],"award-info":[{"award-number":["N00014-15-1-2291"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1007\/s11263-020-01344-9","type":"journal-article","created":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T06:02:32Z","timestamp":1596952952000},"page":"2704-2730","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Densifying Supervision for Fine-Grained Visual Comparisons"],"prefix":"10.1007","volume":"128","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5920-7610","authenticated-orcid":false,"given":"Aron","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,9]]},"reference":[{"key":"1344_CR1","doi-asserted-by":"crossref","unstructured":"Alabdulmohsin, I. Gao, X., & Zhang, X. (2015). Efficient active learning of halfspaces via query synthesis. In AAAI.","DOI":"10.1609\/aaai.v29i1.9563"},{"key":"1344_CR2","doi-asserted-by":"crossref","unstructured":"Altwaijry, H., & Belongie, S., (2012). Relative ranking of facial attractiveness. In Winter conference on applications of computer vision (WACV).","DOI":"10.1109\/WACV.2013.6475008"},{"key":"1344_CR3","doi-asserted-by":"crossref","unstructured":"Angluin, D. (1988). Queries and concept learning. In Machine learning.","DOI":"10.1007\/BF00116828"},{"key":"1344_CR4","unstructured":"Baum, E., & Lang, K. (1992). Query learning can work poorly when a human oracle is used. In IJCNN."},{"key":"1344_CR5","doi-asserted-by":"crossref","unstructured":"Biswas, A., & Parikh, D. (2013). Simultaneous active learning of classifiers and attributes via relative feedback. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2013.89"},{"key":"1344_CR6","doi-asserted-by":"crossref","unstructured":"Branson, S., Wah, C., Schroff, F., Babenko, B., Welinder, P., Perona, P., & Belongie, S. (2010). Visual recognition with humans in the loop. In Proceedings of European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-642-15561-1_32"},{"key":"1344_CR7","unstructured":"Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., et al. (2015). Learning to rank using gradient descent. In Proceedings of international conference on machine learning (ICML)."},{"key":"1344_CR8","doi-asserted-by":"crossref","unstructured":"Cai, J., Zha, Z., Wang, M., Zhang, S., & Tian, Q. (2015). An Attribute-assisted reranking model for web image search. IEEE Transactions on Image Processing","DOI":"10.1109\/TIP.2014.2372616"},{"key":"1344_CR9","doi-asserted-by":"crossref","unstructured":"Cao, C., Kwak, I., Belongie, S., Kriegman, D., & Ai, H. (2014). Adaptive ranking of facial attractiveness. In International conference on multimedia and expo (ICME).","DOI":"10.1109\/ICME.2014.6890147"},{"key":"1344_CR10","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Chao, W.-L., & Sha, F. (2017). Predicting visual exemplars of unseen classes for zero-shot learning. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.376"},{"key":"1344_CR11","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Kalogerakis, E., Giguere, S., & Funkhouser, T. (2013). AttribIt: Content creation with semantic attributes. In ACM symposium on user interface software and technology (UIST).","DOI":"10.1145\/2501988.2502008"},{"key":"1344_CR12","doi-asserted-by":"crossref","unstructured":"Chen, K., Gong, S., Xiang, T., & Loy, C. (2013). Cumulative attribute space for age and crowd density estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2013.319"},{"key":"1344_CR13","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, Q., & Li, B. (2014). Predicting multiple attributes via relative multi-task learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2014.135"},{"key":"1344_CR14","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., & Choo, J. (2018). Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00916"},{"key":"1344_CR15","doi-asserted-by":"crossref","unstructured":"Datta, A., Feris, R., & Vaquero, D. (2011). Hierarchical Ranking of Facial Attributes. In Face and gesture.","DOI":"10.1109\/FG.2011.5771429"},{"key":"1344_CR16","doi-asserted-by":"crossref","unstructured":"Demirel, B., Cinbis, R. G., & Ikizler-Cinbis, N. (2017). Attributes2Classname: a discriminative model for attribute-based unsupervised zero-shot learning. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.139"},{"key":"1344_CR17","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1344_CR18","doi-asserted-by":"crossref","unstructured":"Dixit, M., Kwitt, R., Niethammer, M., & Vasconcelos, N. (2017). AGA: attribute-guided augmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.355"},{"key":"1344_CR19","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Springenberg, J., & Brox, T. (2015). Learning to generate chairs with convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"1344_CR20","unstructured":"Dosovitskiy, A., Springenberg, J., Riedmiller, M., & Brox, T. (2014). Discriminative unsupervised feature learning with convolutional neural networks. In Advances in neural information processing systems (NIPS)."},{"key":"1344_CR21","doi-asserted-by":"crossref","unstructured":"Fan, Q., Gabbur, P., & Pankanti, S. (2013). Relative attributes for large-scale abandoned object detection. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2013.340"},{"key":"1344_CR22","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., & Forsyth, D. (2009). Describing objects by their attributes. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPRW.2009.5206772"},{"key":"1344_CR23","doi-asserted-by":"crossref","unstructured":"Farrell, R., Oza, O., Zhang, N., Morariu, V., Darrell, T., & Davis, L. (2011). Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2011.6126238"},{"key":"1344_CR24","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., Girshick, R., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 32(9).","DOI":"10.1109\/TPAMI.2009.167"},{"key":"1344_CR25","unstructured":"Freedman, D. (2010). Why scientific studies are so often wrong: The streetlight effect. Discover."},{"key":"1344_CR26","doi-asserted-by":"crossref","unstructured":"Freytag, A., Rodner, E., & Denzler, J. (2014). Selecting influential examples: active learning with expected model output changes. In ECCV.","DOI":"10.1007\/978-3-319-10593-2_37"},{"key":"1344_CR27","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems (NIPS)."},{"key":"1344_CR28","unstructured":"Gregor, K., Danihelka, I., Graves, A., & Wierstra, D. (2015). DRAW: A recurrent neural network for image generation. In Proceedings of international conference on machine learning (ICML)."},{"key":"1344_CR29","doi-asserted-by":"crossref","unstructured":"Hariharan, B., & Girshick, R. (2017). Low-shot visual recognition by shrinking and hallucinating features. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.328"},{"key":"1344_CR30","unstructured":"Hauberg, S., Freifeld, O., Larsen, A., Fisher, J., & Hansen, L. (2017). Dreaming more data: Class-dependent distributions over diffeomorphisms for learned data augmentation. In International conference on artificial intelligence and statistics."},{"key":"1344_CR31","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2017). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision (ICCV)."},{"key":"1344_CR32","unstructured":"Huang, G. B., Ramesh, M., Berg, T., & Learned-Miller, E. (2007). Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical report, University of Massachusetts, Amherst."},{"key":"1344_CR33","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., & Kautz, J. (2018). Multimodal unsupervised image-to-image translation. In ECCV.","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"1344_CR34","doi-asserted-by":"crossref","unstructured":"Huijser, M. W., & van Gemert, J. C. (2017). Active decision boundary annotation with deep generative models. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.565"},{"key":"1344_CR35","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2017.632"},{"key":"1344_CR36","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Synthetic data and artificial neural networks for natural scene text recognition. In NIPS 14 deep learning workshop."},{"key":"1344_CR37","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015). Spatial transformer networks. In Advances in neural information processing systems (NIPS)."},{"key":"1344_CR38","doi-asserted-by":"crossref","unstructured":"Joachims, T. (2002). Optimizing search engines using clickthrough data. In Knowledge discovery in databases (PKDD).","DOI":"10.1145\/775047.775067"},{"key":"1344_CR39","doi-asserted-by":"crossref","unstructured":"Kalayeh, M.\u00a0M., Gong, B., & Shah, M. (2017). Improving facial attribute prediction using semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.450"},{"key":"1344_CR40","doi-asserted-by":"crossref","unstructured":"Kemelmacher-Shlizerman, I., Suwajanakorn, S., & Seitz, S. (2014). Illumination-aware age progression. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2014.426"},{"key":"1344_CR41","unstructured":"Khoreva, A., Benenson, R., Ilg, E., Brox, T., & Schiele, B. (2017). Lucid data dreaming for object tracking. Technical Report arXiv:1703.09554,"},{"key":"1344_CR42","doi-asserted-by":"crossref","unstructured":"Khosla, A., Bainbridge, W. A., Torralba, A., & Oliva, A. (2013). Modifying the memorability of face photographs. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2013.397"},{"key":"1344_CR43","unstructured":"Kingma, D., & Welling, M. (2014). Auto-encoding variational bayes. In Proceedings international conference on learning representations (ICLR)."},{"key":"1344_CR44","doi-asserted-by":"crossref","unstructured":"Kovashka, A., & Grauman, K. (2013). Attribute pivots for guiding relevance feedback in image search. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2013.44"},{"key":"1344_CR45","doi-asserted-by":"crossref","unstructured":"Kovashka, A., Parikh, D., & Grauman, K. (2012). WhittleSearch: Image search with relative attribute feedback. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2012.6248026"},{"issue":"2","key":"1344_CR46","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s11263-015-0814-0","volume":"115","author":"A Kovashka","year":"2015","unstructured":"Kovashka, A., Parikh, D., & Grauman, K. (2015). WhittleSearch: Interactive image search with relative attribute feedback. International Journal of Computer Vision (IJCV), 115(2), 185\u2013210.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1344_CR47","unstructured":"Kulkarni, T., Whitney, W., Kohli, P., & Tenenbaum, J. (2015). Deep convolutional inverse graphics network. In Advances in neural information processing systems (NIPS)."},{"key":"1344_CR48","doi-asserted-by":"crossref","unstructured":"Kumar, N., Belhumeur, P., & Nayar, S. (2008). FaceTracer: A search engine for large collections of images with faces. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-540-88693-8_25"},{"key":"1344_CR49","doi-asserted-by":"crossref","unstructured":"Kwitt, R., Hegenbart, S., & Niethammer, M. (2016). One-shot learning of scene locations via feature trajectory transfer. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.16"},{"key":"1344_CR50","doi-asserted-by":"crossref","unstructured":"Laffont, P., Ren, Z., Tao, X., Qian, C., & Hays, J. (2014). Transient attributes for high-level understanding and editing of outdoor scenes. In SIGGRAPH.","DOI":"10.1145\/2601097.2601101"},{"key":"1344_CR51","doi-asserted-by":"crossref","unstructured":"Lampert, C., Nickisch, H., Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In Conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPRW.2009.5206594"},{"key":"1344_CR52","unstructured":"Lample, G., Zeghidour, N., Usunier, N., Bordes, A., Denoyer, L., et\u00a0al. (2017). Fader networks: Manipulating images by sliding attributes. In NIPS (pp. 5963\u20135972)."},{"key":"1344_CR53","unstructured":"Li, S., Shan, S., & Chen, X. (2012). Relative forest for attribute prediction. In Asian conference on computer vision (ACCV)."},{"key":"1344_CR54","unstructured":"Li, M., Zuo, W., & Zhang, D. (2016). Convolutional network for attribute-driven and identity-preserving human face generation. Technical Report arXiv:1608.06434,"},{"key":"1344_CR55","doi-asserted-by":"crossref","unstructured":"Liang, L., & Grauman, K. (2014). Beyond comparing image pairs: Setwise active learning for relative attributes. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2014.34"},{"key":"1344_CR56","doi-asserted-by":"crossref","unstructured":"Lu, Y., Tai, Y.-W., & Tang, C.-K. (2018). Attribute-guided face generation using conditional cyclegan. In Proceedings of European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01258-8_18"},{"key":"1344_CR57","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten, L., & Hinton, G. (2008). Visualizing High-Dimensional Data Using t-SNE. Journal of Machine Learning Research (JMLR), 9, 2579\u20132605.","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"1344_CR58","doi-asserted-by":"crossref","unstructured":"Maji, S. (2012). Discovering a lexicon of parts and attributes. In Second international workshop on parts and attributes, ECCV.","DOI":"10.1007\/978-3-642-33885-4_3"},{"key":"1344_CR59","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft. Technical Report arXiv:1306.5151."},{"key":"1344_CR60","doi-asserted-by":"crossref","unstructured":"Matthews, T., Nixon, M. & Niranjan, M. (2013). Enriching texture analysis with semantic data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),","DOI":"10.1109\/CVPR.2013.165"},{"key":"1344_CR61","doi-asserted-by":"crossref","unstructured":"Meng, Z., Adluru, N., Kim, H.\u00a0J., Fung, G., & Singh, V. (2018). Efficient relative attribute learning using graph neural networks. In Proceedings of European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01264-9_34"},{"key":"1344_CR62","doi-asserted-by":"crossref","unstructured":"Miller, E., Matsakis, N., & Viola, P. (2000). Learning from one example through shared densities on transforms. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2000.855856"},{"key":"1344_CR63","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S., Fawzi, A., & Frossard, P. (2016). DeepFool: A simple and accurate method to fool deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.282"},{"key":"1344_CR64","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J., & Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"1344_CR65","doi-asserted-by":"crossref","unstructured":"O\u2019Donovan, P., Libeks, J., Agarwala, A., & Hertzmann, A. (2014). Exploratory font selection using crowdsourced attributes. In SIGGRAPH.","DOI":"10.1145\/2601097.2601110"},{"key":"1344_CR66","doi-asserted-by":"crossref","unstructured":"Pandey, G., & Dukkipati, A. (2016). Variational methods for conditional multimodal learning: Generating human faces from attributes. Technical Report arXiv:1603.01801.","DOI":"10.1109\/IJCNN.2017.7965870"},{"key":"1344_CR67","doi-asserted-by":"crossref","unstructured":"Parikh, D., & Grauman, K. (2011). Relative attributes. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"1344_CR68","doi-asserted-by":"crossref","unstructured":"Park, D., & Ramanan, D. (2015). Articulated pose estimation with tiny synthetic videos. In ChaLearn workshop, CVPR.","DOI":"10.1109\/CVPRW.2015.7301337"},{"key":"1344_CR69","doi-asserted-by":"crossref","unstructured":"Paulin, M., Revaud, J., Harchaoui, Z., Perronnin, F., & Schmid, C. (2014). Transformation pursuit for image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2014.466"},{"key":"1344_CR70","doi-asserted-by":"crossref","unstructured":"Peng, X., Sun, B., Ali, K., & Saenko, K. (2015). Learning deep object detectors from 3D models. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.151"},{"key":"1344_CR71","doi-asserted-by":"crossref","unstructured":"Peng, X., Tang, Z., Yang, F., Feris, R.\u00a0S., & Metaxas, D. (2018). Jointly optimize data augmentation and network training: Adversarial data augmentation in human pose estimation. In CVPR.","DOI":"10.1109\/CVPR.2018.00237"},{"key":"1344_CR72","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Jain, A., Wojek, C., Thormahlen, T., & Schiele, B. (2011). In good shape: Robust people detection based on appearance and shape. In British machine vision conference (BMVC).","DOI":"10.5244\/C.25.5"},{"key":"1344_CR73","unstructured":"Qian, B., Wang, X., Wang, F., Li, H., Ye, J., & Davidson, I. (2013). Active learning from relative queries. In IJCAI international joint conference on artificial intelligence."},{"key":"1344_CR74","unstructured":"Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. In ICLR."},{"key":"1344_CR75","doi-asserted-by":"crossref","unstructured":"Reid, D., & Nixon, M. (2013). Human identification using facial comparative descriptions. In ICB.","DOI":"10.1109\/ICB.2013.6612962"},{"key":"1344_CR76","doi-asserted-by":"crossref","unstructured":"Reid, D., & Nixon, M. (2014). Using comparative human descriptions for soft biometrics. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 36.","DOI":"10.1109\/TPAMI.2013.219"},{"key":"1344_CR77","doi-asserted-by":"crossref","unstructured":"Sadovnik, A., Gallagher, A., Parikh, D., & Chen, T. (2013). Spoken attributes: Mixing binary and relative attributes to say the right thing. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2013.268"},{"key":"1344_CR78","doi-asserted-by":"crossref","unstructured":"Sandeep, R., Verma, Y., & Jawahar, C. (2014). Relative parts: Distinctive parts for learning relative attributes. In Conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2014.462"},{"key":"1344_CR79","unstructured":"Settles, B. (2010). Active learning literature survey. Technical report."},{"key":"1344_CR80","doi-asserted-by":"crossref","unstructured":"Shakhnarovich, G., Viola, P., & Darrell, T. (2003). Fast pose estimation with parameter-sensitive hashing. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2003.1238424"},{"key":"1344_CR81","doi-asserted-by":"crossref","unstructured":"Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., & Blake, A. (2011). Real-time human pose recognition in parts from single depth images. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"1344_CR82","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., & Girshick, R. (2016). Training region-based object detectors with online hard example mining. In CVPR.","DOI":"10.1109\/CVPR.2016.89"},{"key":"1344_CR83","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., & Webb, R. (2017). Learning from simulated and unsupervised images through adversarial training. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.241"},{"key":"1344_CR84","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Singh, S., & Gupta, A. (2012). Constrained semi-supervised learning using attributes and comparative attributes. In Proceedings of European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-642-33712-3_27"},{"key":"1344_CR85","doi-asserted-by":"crossref","unstructured":"Siddiquie, B., Feris, R., & Davis, L. (2011). Image ranking and retrieval based on multi-attribute queries. In CVPR.","DOI":"10.1109\/CVPR.2011.5995329"},{"key":"1344_CR86","doi-asserted-by":"crossref","unstructured":"Simard, P., Steinkraus, D., & Platt, J. (2003). Best practices for convolutional neural networks applied to visual document analysis. In ICDAR.","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"1344_CR87","doi-asserted-by":"crossref","unstructured":"Singh, K., & Lee, Y.\u00a0J. (2016). End-to-end localization and ranking for relative attributes. In Proceedings of European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46466-4_45"},{"key":"1344_CR88","unstructured":"Souri, Y., Noury, E., & Adeli, E. (2016). Deep relative attributes. In Asian conference on computer vision (ACCV)."},{"key":"1344_CR89","doi-asserted-by":"crossref","unstructured":"Su, J.-C., Wu, C., Jiang, H., & Maji, S. (2017). Reasoning about fine-grained attribute phrases using reference games. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.53"},{"key":"1344_CR90","unstructured":"Tong, S., & Koller, D. (1998). Support vector machine active learning with applications to text classification. In ICML."},{"key":"1344_CR91","doi-asserted-by":"crossref","unstructured":"Upchurch, P., Pleiss, J.\u00a0G.\u00a0G., Pless, R., Snavely, N., Bala, K., & Weinberger, K. (2017). Deep feature interpolation for image content changes. In CVPR.","DOI":"10.1109\/CVPR.2017.645"},{"key":"1344_CR92","doi-asserted-by":"crossref","unstructured":"Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M.\u00a0J., Laptev, I., & Schmid, C. (2017). Learning from synthetic humans. In CVPR.","DOI":"10.1109\/CVPR.2017.492"},{"key":"1344_CR93","doi-asserted-by":"crossref","unstructured":"Verma, V., Arora, G., Mishra, A., & Rai, P. (2018). Generalized zero-shot learning via synthesized examples. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00450"},{"key":"1344_CR94","doi-asserted-by":"crossref","unstructured":"Vijayanarasimhan, S., & Grauman, K. (2009). What\u2019s it going to cost you?: Predicting effort vs. informativeness for multi-label image annotations. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPRW.2009.5206705"},{"issue":"1","key":"1344_CR95","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s11263-014-0721-9","volume":"108","author":"S Vijayanarasimhan","year":"2014","unstructured":"Vijayanarasimhan, S., & Grauman, K. (2014). Large-scale live active learning: Training object detectors with crawled data and crowds. International Journal of Computer Vision (IJCV), 108(1), 97\u2013114.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1344_CR96","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of international conference on machine learning (ICML).","DOI":"10.1145\/1390156.1390294"},{"key":"1344_CR97","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., & Akata, Z. (2018). Feature generating networks for zero-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00581"},{"key":"1344_CR98","doi-asserted-by":"crossref","unstructured":"Xiao, F., & Lee, Y. J. (2015). Discovering the spatial extent of relative attributes. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.171"},{"key":"1344_CR99","doi-asserted-by":"crossref","unstructured":"Yan, X., Yang, J., Sohn, K., & Lee, H. (2016). Attribute2Image: Conditional image generation from visual attributes. In Proceedings of European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"1344_CR100","doi-asserted-by":"crossref","unstructured":"Yan, X., Yang, J., Sohn, K., & Lee, H. (2016). Attribute2Image: Conditional image generation from visual attributes. Technical Report arXiv:1512.00570.","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"1344_CR101","doi-asserted-by":"crossref","unstructured":"Yang, D., & Deng, J. (2017). Shape from shading through shape evolution. Technical Report arXiv:1712.02961.","DOI":"10.1109\/CVPR.2018.00398"},{"key":"1344_CR102","doi-asserted-by":"crossref","unstructured":"Yang, L., Luo, P., Loy, C.\u00a0C., & Tang, X. (2015). A large-scale car dataset for fine-grained categorization and verification. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"1344_CR103","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, T., Xu, C., Yan, S., Hossain, M., & Ghoneim, A. (2016). Deep relative attributes. IEEE Transactions on Multimedia, 18(9).","DOI":"10.1109\/TMM.2016.2582379"},{"key":"1344_CR104","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., & Mei, T. (2017). Boosting image captioning with attributes. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.524"},{"key":"1344_CR105","doi-asserted-by":"crossref","unstructured":"Yu, A., & Grauman, K. (2014). Fine-grained visual comparisons with local learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2014.32"},{"key":"1344_CR106","doi-asserted-by":"crossref","unstructured":"Yu, A., & Grauman, K. (2017). Semantic Jitter: Dense supervision for visual comparisons via synthetic images. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.594"},{"key":"1344_CR107","doi-asserted-by":"crossref","unstructured":"Yu, A., & Grauman, K. (2019). Thinking outside the pool: Active training image creation for relative attributes. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00080"},{"issue":"4","key":"1344_CR108","doi-asserted-by":"publisher","first-page":"86:1","DOI":"10.1145\/2766908","volume":"34","author":"ME Yumer","year":"2015","unstructured":"Yumer, M. E., Chaudhuri, S., Hodgins, J. K., & Kara, L. B. (2015). Semantic shape editing using deformation handles. ACM Transactions on Graphics, 34(4), 86:1\u201386:12.","journal-title":"ACM Transactions on Graphics"},{"key":"1344_CR109","doi-asserted-by":"crossref","unstructured":"Zhang, G., Kan, M., Shan, S., & Chen, X. (2018). Generative adversarial network with spatial attention for face attribute editing. In ECCV.","DOI":"10.1007\/978-3-030-01231-1_26"},{"key":"1344_CR110","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X. & Metaxas, D. (2017) Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In ICCV.","DOI":"10.1109\/ICCV.2017.629"},{"key":"1344_CR111","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Song, S., Yumer, E., Savva, M., Lee, J., Jin, H., & Funkhouser, T. (2017). Physically-based rendering for indoor scene understanding using convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2017.537"},{"key":"1344_CR112","unstructured":"Zhao, L., Sukthankar, G., & Sukthankar, R. (2011). Robust active learning using crowdsourced annotations for activity recognition. In HCOMP."},{"key":"1344_CR113","unstructured":"Zhu, J.-J., & Bento, J. (2017). Generative adversarial active learning. Technical Report arXiv:1702.07956."},{"key":"1344_CR114","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.244"},{"key":"1344_CR115","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Elhoseiny, M., Liu, B., Peng, X., & Elgammal, A. (2018). A generative adversarial approach for zero-shot learning from noisy texts. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00111"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01344-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01344-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01344-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,6]],"date-time":"2022-11-06T08:55:38Z","timestamp":1667724938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01344-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,9]]},"references-count":115,"journal-issue":{"issue":"10-11","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["1344"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01344-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,9]]},"assertion":[{"value":"1 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}