{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:37:13Z","timestamp":1789234633792,"version":"build-2803163510"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T00:00:00Z","timestamp":1691884800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T00:00:00Z","timestamp":1691884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132002"],"award-info":[{"award-number":["62132002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202010"],"award-info":[{"award-number":["62202010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M710212"],"award-info":[{"award-number":["2022M710212"]}],"id":[{"id":"10.13039\/501100002858","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":[[2023,12]]},"DOI":"10.1007\/s11263-023-01849-z","type":"journal-article","created":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T15:01:21Z","timestamp":1691938881000},"page":"3289-3306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Semantic Contrastive Bootstrapping for Single-Positive Multi-label Recognition"],"prefix":"10.1007","volume":"131","author":[{"given":"Cheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4346-8696","authenticated-orcid":false,"given":"Jia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,13]]},"reference":[{"key":"1849_CR1","unstructured":"Balcan, M. F. F., Sharma, D. (2021). Data driven semi-supervised learning. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR2","doi-asserted-by":"crossref","unstructured":"Bar, A., Wang, X., Kantorov, V., Reed, C. J., Herzig, R., Chechik, G., Rohrbach, A., Darrell, T., & Globerson, A. (2022). Detreg: Unsupervised pretraining with region priors for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14605\u201314615).","DOI":"10.1109\/CVPR52688.2022.01420"},{"key":"1849_CR3","doi-asserted-by":"publisher","unstructured":"Bucak, S. S., Jin, R., & Jain, A. K. (2011). Multi-label learning with incomplete class assignments. In 2011 IEEE conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR.2011.5995734.","DOI":"10.1109\/CVPR.2011.5995734"},{"key":"1849_CR4","unstructured":"Cabral, R., Torre, F., Costeira, J. P., & Bernardino, A. (2011). Matrix completion for multi-label image classification. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR5","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European conference on computer vision (ECCV), https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1849_CR6","doi-asserted-by":"publisher","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., & Balasubramanian, V. N. (2018). Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. In 2018 IEEE winter conference on applications of computer vision (WACV), https:\/\/doi.org\/10.1109\/WACV.2018.00097.","DOI":"10.1109\/WACV.2018.00097"},{"key":"1849_CR7","doi-asserted-by":"crossref","unstructured":"Chen, T., Xu, M., Hui, X., Wu, H., & Lin, L. (2019a). Learning semantic-specific graph representation for multi-label image recognition. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2019.00061"},{"key":"1849_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th international conference on machine learning (ICML)."},{"key":"1849_CR9","doi-asserted-by":"crossref","unstructured":"Chen, T., Pu, T., Wu, H., Xie, Y., & Lin, L. (2021). Structured semantic transfer for multi-label recognition with partial labels.","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"1849_CR10","first-page":"69","volume":"5","author":"T Chen","year":"2022","unstructured":"Chen, T., Lin, L., Chen, R., Hui, X., & Wu, H. (2022). Knowledge-guided multi-label few-shot learning for general image recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence, 5, 69.","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"1849_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z. M., Wei, X. S., Wang, P., & Guo, Y. (2019b). Multi-label image recognition with graph convolutional networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00532"},{"key":"1849_CR12","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., & Shen, C. (2021). Twins: Revisiting the design of spatial attention in vision transformers. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR13","doi-asserted-by":"crossref","unstructured":"Cole, E., Mac\u00a0Aodha, O., Lorieul, T., Perona, P., Morris, D., & Jojic, N. (2021). Multi-label learning from single positive labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00099"},{"key":"1849_CR14","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., & Chen, J. (2021). Up-detr: Unsupervised pre-training for object detection with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 1601\u20131610).","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"1849_CR15","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\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1849_CR16","unstructured":"Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American Chapter of the Association for computational linguistics: Human Language Technologies."},{"key":"1849_CR17","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021a). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations."},{"key":"1849_CR18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021b). An image is worth 16 x 16 words: Transformers for image recognition at scale. In International conference on learning representations."},{"key":"1849_CR19","doi-asserted-by":"crossref","unstructured":"Durand, T., Mehrasa, N., & Mori, G. (2019). Learning a deep convnet for multi-label classification with partial labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00074"},{"key":"1849_CR20","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2007). The PASCAL visual object classes challenge 2007 (VOC2007) results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html"},{"key":"1849_CR21","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2012). The PASCAL visual object classes challenge 2012 (VOC2012) results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"key":"1849_CR22","doi-asserted-by":"publisher","first-page":"5920","DOI":"10.1109\/TIP.2021.3088605","volume":"30","author":"BB Gao","year":"2021","unstructured":"Gao, B. B., & Zhou, H. Y. (2021). Learning to discover multi-class attentional regions for multi-label image recognition. IEEE Transactions on Image Processing, 30, 5920\u20135932.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1849_CR23","doi-asserted-by":"crossref","unstructured":"Ge, W., Yang, S., & Yu, Y. (2018). Multi-evidence filtering and fusion for multi-label classification, object detection and semantic segmentation based on weakly supervised learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00139"},{"key":"1849_CR24","unstructured":"Gong, X., Yuan, D., & Bao, W. (2021). Understanding partial multi-label learning via mutual information. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR25","unstructured":"Grill, J. B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila\u00a0Pires, B., Guo, Z., Gheshlaghi\u00a0Azar, M., Piot, B., kavukcuoglu, k., Munos, R., & Valko, M. (2020). Bootstrap your own latent-a new approach to self-supervised learning. In: Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR26","doi-asserted-by":"crossref","unstructured":"Guo, H., & Wang, S. (2021). Long-tailed multi-label visual recognition by collaborative training on uniform and re-balanced samplings. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.01484"},{"key":"1849_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1849_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1849_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2021). Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1849_CR30","unstructured":"Hu, H., Xie, L., Du, Z., Hong, R., & Tian, Q. (2020). One-bit supervision for image classification. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR31","doi-asserted-by":"crossref","unstructured":"Huynh, D., & Elhamifar, E. (2020). Interactive multi-label CNN learning with partial labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00944"},{"key":"1849_CR32","doi-asserted-by":"crossref","unstructured":"Jia, J., Chen, X., & Huang, K. (2021). Spatial and semantic consistency regularizations for pedestrian attribute recognition. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00100"},{"key":"1849_CR33","unstructured":"Jiang, L., Zhou, Z., Leung, T., Li, L.J., & Fei-Fei, L. (2018). MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In Proceedings of the 35th international conference on machine learning (ICML)."},{"key":"1849_CR34","unstructured":"Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020). Supervised contrastive learning. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR35","unstructured":"Li, Z., Chen, Z., Yang, F., Li, W., Zhu, Y., Zhao, C., Deng, R., Wu, L., Zhao, R., Tang, M., & Wang, J. (2021). Mst: Masked self-supervised transformer for visual representation. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR36","doi-asserted-by":"crossref","unstructured":"Li, Z., Zhu, Y., Yang, F., Li, W., Zhao, C., Chen, Y., Chen, Z., Xie, J., Wu, L., Zhao, R., Tang, M., & Wang, J. (2022). Univip: A unified framework for self-supervised visual pre-training.","DOI":"10.1109\/CVPR52688.2022.01422"},{"key":"1849_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"9","key":"1849_CR38","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1007\/s11263-019-01174-4","volume":"127","author":"H Liu","year":"2019","unstructured":"Liu, H., Wang, R., Shan, S., & Chen, X. (2019). Deep supervised hashing for fast image retrieval. International Journal of Computer Vision, 127(9), 1217\u20131234. https:\/\/doi.org\/10.1007\/s11263-019-01174-4","journal-title":"International Journal of Computer Vision"},{"key":"1849_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Y., Sheng, L., Shao, J., Yan, J., Xiang, S., & Pan, C. (2018). Multi-label image classification via knowledge distillation from weakly-supervised detection. In Proceedings of the 26th ACM international conference on multimedia.","DOI":"10.1145\/3240508.3240567"},{"key":"1849_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1849_CR41","unstructured":"Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"1849_CR42","doi-asserted-by":"crossref","unstructured":"Pu, T., Chen, T., Wu, H., & Lin, L. (2022). Semantic-aware representation blending for multi-label image recognition with partial labels. In Proceedings of the AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v36i2.20105"},{"key":"1849_CR43","unstructured":"Rao, Y., Zhao, W., Zhu, Z., Lu, J., & Zhou, J. (2021). Global filter networks for image classification. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR44","unstructured":"Sener O, & Koltun V (2018) Multi-task learning as multi-objective optimization. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR45","unstructured":"Shao, Z., Bian, H., Chen, Y., Wang, Y., Zhang, J., Ji, X., & zhang, y. (2021). Transmil: Transformer based correlated multiple instance learning for whole slide image classification. In Advances in neural information processing systems (NeurIPS)."},{"issue":"2","key":"1849_CR46","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/s11263-021-01547-8","volume":"130","author":"A Shin","year":"2022","unstructured":"Shin, A., Ishii, M., & Narihira, T. (2022). Perspectives and prospects on transformer architecture for cross-modal tasks with language and vision. International Journal of Computer Vision, 130(2), 435\u2013454. https:\/\/doi.org\/10.1007\/s11263-021-01547-8","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"1849_CR47","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11263-020-01397-w","volume":"129","author":"L Song","year":"2021","unstructured":"Song, L., Liu, J., Sun, M., & Shang, X. (2021). Weakly supervised group mask network for object detection. International Journal of Computer Vision, 129(3), 681\u2013702. https:\/\/doi.org\/10.1007\/s11263-020-01397-w","journal-title":"International Journal of Computer Vision"},{"key":"1849_CR48","unstructured":"Tsipras, D., Santurkar, S., Engstrom, L., Ilyas, A., & Madry, A. (2020). From imagenet to image classification: Contextualizing progress on benchmarks. In Proceedings of the 37th international conference on machine learning (ICML)."},{"key":"1849_CR49","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101","author":"G Tsoumakas","year":"2009","unstructured":"Tsoumakas, G., & Katakis, I. (2009). Multi-label classification: An overview. International Journal of Data Warehousing and Mining. https:\/\/doi.org\/10.4018\/jdwm.2007070101","journal-title":"International Journal of Data Warehousing and Mining"},{"key":"1849_CR50","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR51","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The caltech-ucsd birds-200-2011 dataset. Technical Report CNS-TR-2011-001, California Institute of Technology"},{"key":"1849_CR52","doi-asserted-by":"crossref","unstructured":"Wang, H., Xiao, R., Li, Y., Feng, L., Niu, G., Chen, G., & Zhao, J. (2022a). Pico: Contrastive label disambiguation for partial label learning.","DOI":"10.1109\/TPAMI.2023.3342650"},{"key":"1849_CR53","doi-asserted-by":"publisher","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., & Xu, W. (2016). Cnn-rnn: A unified framework for multi-label image classification. In 2016 IEEE conference on computer vision and pattern recognition (CVPR)https:\/\/doi.org\/10.1109\/CVPR.2016.251.","DOI":"10.1109\/CVPR.2016.251"},{"key":"1849_CR54","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, Z., De\u00a0Mello, S., Kautz, J., Anandkumar, A., Shen, C., & Alvarez, J.M. (2022b). Freesolo: Learning to segment objects without annotations. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14176\u201314186).","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"1849_CR55","unstructured":"Wang, Y., Huang, R., Song, S., Huang, Z., & Huang, G. (2021). Not all images are worth 16 x 16 words: Dynamic transformers for efficient image recognition. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR56","doi-asserted-by":"publisher","DOI":"10.1038\/435439a","author":"JM Wolfe","year":"2005","unstructured":"Wolfe, J. M., Horowitz, T. S., & Kenner, N. M. (2005). Rare items often missed in visual searches. Nature. https:\/\/doi.org\/10.1038\/435439a","journal-title":"Nature"},{"key":"1849_CR57","first-page":"96","volume":"5","author":"B Wu","year":"2018","unstructured":"Wu, B., Jia, F., Liu, W., Ghanem, B., & Lyu, S. (2018). Multi-label learning with missing labels using mixed dependency graphs. International Journal of Computer Vision, 5, 96.","journal-title":"International Journal of Computer Vision"},{"key":"1849_CR58","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2956775","author":"B Wu","year":"2019","unstructured":"Wu, B., Chen, W., Fan, Y., Zhang, Y., Hou, J., Liu, J., & Zhang, T. (2019). Tencent ML-images: A large-scale multi-label image database for visual representation learning. IEEE Access. https:\/\/doi.org\/10.1109\/access.2019.2956775","journal-title":"IEEE Access"},{"key":"1849_CR59","doi-asserted-by":"crossref","unstructured":"Xie, E., Ding, J., Wang, W., Zhan, X., Xu, H., Sun, P., Li, Z., & Luo, P. (2021a). Detco: Unsupervised contrastive learning for object detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8392\u20138401).","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"1849_CR60","unstructured":"Xie, J., Zhan, X., Liu, Z., Ong, Y. S., & Loy, C. C. (2021b). Unsupervised object-level representation learning from scene images. Advances in Neural Information Processing Systems 34, 28864\u201328876."},{"key":"1849_CR61","unstructured":"Xu, M., Jin, R., & Zhou, Z.H. (2013). Speedup matrix completion with side information: Application to multi-label learning. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR62","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhou, J. T., & Cai, J. (2016). Improving multi-label learning with missing labels by structured semantic correlations. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46448-0_50"},{"key":"1849_CR63","unstructured":"Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., & Wang, J. (2021). Hrformer: High-resolution vision transformer for dense predict. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR64","doi-asserted-by":"crossref","unstructured":"Yun, S., Oh, S. J., Heo, B., Han, D., Choe, J., & Chun, S. (2021). Re-labeling imagenet: From single to multi-labels, from global to localized labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00237"},{"key":"1849_CR65","unstructured":"Zhang, B., Wang, Y., Hou, W., WU, H., Wang, J., Okumura, M., & Shinozaki, T. (2021a). Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. In Advances in neural information processing systems (NeurIPS)."},{"issue":"4","key":"1849_CR66","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/s11263-018-1112-4","volume":"127","author":"D Zhang","year":"2019","unstructured":"Zhang, D., Han, J., Zhao, L., & Meng, D. (2019). Leveraging prior-knowledge for weakly supervised object detection under a collaborative self-paced curriculum learning framework. International Journal of Computer Vision, 127(4), 363\u2013380. https:\/\/doi.org\/10.1007\/s11263-018-1112-4","journal-title":"International Journal of Computer Vision"},{"key":"1849_CR67","unstructured":"Zhang, W., Pang, J., Chen, K., & Loy, C.C. (2021b). K-net: Towards unified image segmentation. In Advances in neural information processing systems (NeurIPS)."},{"key":"1849_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, J., Yan, K., Zhao, Y., Guo, X., Huang, F., & Li, J. (2021). Transformer-based dual relation graph for multi-label image recognition. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00023"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01849-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01849-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01849-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T23:38:46Z","timestamp":1702942726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01849-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,13]]},"references-count":68,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1849"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01849-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,13]]},"assertion":[{"value":"3 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}