{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:12:29Z","timestamp":1775578349624,"version":"3.50.1"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T00:00:00Z","timestamp":1535414400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s11263-018-1112-4","type":"journal-article","created":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T23:30:15Z","timestamp":1535499015000},"page":"363-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":134,"title":["Leveraging Prior-Knowledge for Weakly Supervised Object Detection Under a Collaborative Self-Paced Curriculum Learning Framework"],"prefix":"10.1007","volume":"127","author":[{"given":"Dingwen","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5545-7217","authenticated-orcid":false,"given":"Junwei","family":"Han","sequence":"additional","affiliation":[]},{"given":"Long","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Deyu","family":"Meng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,28]]},"reference":[{"key":"1112_CR1","doi-asserted-by":"crossref","unstructured":"Alexe, B., Deselaers, T., & Ferrari, V. (2010). What is an object? In CVPR.","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"1112_CR2","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. In ICML.","DOI":"10.1145\/1553374.1553380"},{"key":"1112_CR3","unstructured":"Bilen, H., Pedersoli, M., & Tuytelaars, T. (2014). Weakly supervised object detection with posterior regularization. In BMVC."},{"key":"1112_CR4","doi-asserted-by":"crossref","unstructured":"Bilen, H., Pedersoli, M., & Tuytelaars, T. (2015). Weakly supervised object detection with convex clustering. In CVPR.","DOI":"10.1109\/CVPR.2015.7298711"},{"key":"1112_CR5","doi-asserted-by":"crossref","unstructured":"Bilen, H., & Vedaldi, A. (2016). Weakly supervised deep detection networks. In CVPR.","DOI":"10.1109\/CVPR.2016.311"},{"key":"1112_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., & Gupta, A. (2015). Webly supervised learning of convolutional networks. In ICCV.","DOI":"10.1109\/ICCV.2015.168"},{"issue":"1","key":"1112_CR7","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TPAMI.2016.2535231","volume":"39","author":"RG Cinbis","year":"2017","unstructured":"Cinbis, R. G., Verbeek, J., & Schmid, C. (2017). Weakly supervised object localization with multi-fold multiple instance learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(1), 189\u2013203.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1112_CR8","doi-asserted-by":"crossref","unstructured":"Deselaers, T., Alexe, B., & Ferrari, V. (2010). Localizing objects while learning their appearance. In ECCV.","DOI":"10.1007\/978-3-642-15561-1_33"},{"issue":"3","key":"1112_CR9","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s11263-012-0538-3","volume":"100","author":"T Deselaers","year":"2012","unstructured":"Deselaers, T., Alexe, B., & Ferrari, V. (2012). Weakly supervised localization and learning with generic knowledge. International Journal of Computer Vision, 100(3), 275\u2013293.","journal-title":"International Journal of Computer Vision"},{"key":"1112_CR10","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Pazandeh, A., Pirsiavash, H., & Van\u00a0Gool, L. (2017). Weakly supervised cascaded convolutional networks. In CVPR.","DOI":"10.1109\/CVPR.2017.545"},{"issue":"2","key":"1112_CR11","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"1112_CR12","unstructured":"Everingham, M., Zisserman, A., Williams, C.\u00a0K., Van\u00a0Gool, L., Allan, M., Bishop, C.\u00a0M., Chapelle, O., Dalal, N., Deselaers, T., Dork\u00f3, G., et\u00a0al. (2007). The pascal visual object classes challenge 2007 (voc2007) results."},{"key":"1112_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast r-cnn. In ICCV.","DOI":"10.1109\/ICCV.2015.169"},{"key":"1112_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2014.81"},{"key":"1112_CR15","doi-asserted-by":"crossref","unstructured":"Gokberk Cinbis, R., Verbeek, J., & Schmid, C. (2014). Multi-fold mil training for weakly supervised object localization. In CVPR.","DOI":"10.1109\/CVPR.2014.309"},{"issue":"4","key":"1112_CR16","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1109\/TIP.2017.2781424","volume":"27","author":"J Han","year":"2018","unstructured":"Han, J., Quan, R., Zhang, D., & Nie, F. (2018a). Robust object co-segmentation using background prior. IEEE Transactions on Image Processing, 27(4), 1639\u20131651.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"1112_CR17","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/MSP.2017.2749125","volume":"35","author":"J Han","year":"2018","unstructured":"Han, J., Zhang, D., Cheng, G., Liu, N., & Xu, D. (2018b). Advanced deep-learning techniques for salient and category-specific object detection: A survey. IEEE Signal Processing Magazine, 35(1), 84\u2013100.","journal-title":"IEEE Signal Processing Magazine"},{"key":"1112_CR18","doi-asserted-by":"crossref","unstructured":"Han, L., Zhang, D., Huang, D., Chang, X., Ren, J., Luo, S., & Han, J. (2017). Self-paced mixture of regressions. In IJCAI.","DOI":"10.24963\/ijcai.2017\/252"},{"key":"1112_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, L., Meng, D., Mitamura, T., & Hauptmann, A.\u00a0G. (2014a). Easy samples first: Self-paced reranking for zero-example multimedia search. In ACM-MM.","DOI":"10.1145\/2647868.2654918"},{"key":"1112_CR20","unstructured":"Jiang, L., Meng, D., Yu, S.-I., Lan, Z., Shan, S., & Hauptmann, A. (2014b). Self-paced learning with diversity. In NIPS."},{"key":"1112_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, L., Meng, D., Zhao, Q., Shan, S., & Hauptmann, A.\u00a0G. (2015). Self-paced curriculum learning. In AAAI.","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"1112_CR22","doi-asserted-by":"crossref","unstructured":"Jie, Z., Wei, Y., Jin, X., Feng, J., & Liu, W. (2017). Deep self-taught learning for weakly supervised object localization. In CVPR.","DOI":"10.1109\/CVPR.2017.457"},{"key":"1112_CR23","doi-asserted-by":"crossref","unstructured":"Kantorov, V., Oquab, M., Cho, M., & Laptev, I. (2016). Contextlocnet: Context-aware deep network models for weakly supervised localization. In ECCV.","DOI":"10.1007\/978-3-319-46454-1_22"},{"key":"1112_CR24","unstructured":"Khan, F., Mutlu, B., & Zhu, X. (2011). How do humans teach: On curriculum learning and teaching dimension. In NIPS."},{"key":"1112_CR25","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.\u00a0E. (2012). Imagenet classification with deep convolutional neural networks. In NIPS."},{"key":"1112_CR26","unstructured":"Kumar, M.\u00a0P., Packer, B., & Koller, D. (2010). Self-paced learning for latent variable models. In NIPS."},{"key":"1112_CR27","doi-asserted-by":"crossref","unstructured":"Kumar Singh, K., Xiao, F., & Jae\u00a0Lee, Y. (2016). Track and transfer: Watching videos to simulate strong human supervision for weakly-supervised object detection. In CVPR.","DOI":"10.1109\/CVPR.2016.386"},{"key":"1112_CR28","doi-asserted-by":"crossref","unstructured":"Li, D., Huang, J.-B., Li, Y., Wang, S., & Yang, M.-H. (2016). Weakly supervised object localization with progressive domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2016.382"},{"key":"1112_CR29","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.\u00a0L., & Dollr, P. (2014). Microsoft coco: Common objects in context. arXiv preprint arXiv:1405.0312 ."},{"key":"1112_CR30","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.ins.2017.05.043","volume":"414","author":"D Meng","year":"2017","unstructured":"Meng, D., Zhao, Q., & Jiang, L. (2017). Theoretical understanding of self-paced learning. Information Sciences, 414, 319\u2013328.","journal-title":"Information Sciences"},{"key":"1112_CR31","doi-asserted-by":"crossref","unstructured":"Pandey, M., & Lazebnik, S. (2011). Scene recognition and weakly supervised object localization with deformable part-based models. In ICCV.","DOI":"10.1109\/ICCV.2011.6126383"},{"issue":"2","key":"1112_CR32","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1109\/TPAMI.2015.2456908","volume":"38","author":"W Ren","year":"2016","unstructured":"Ren, W., Huang, K., Tao, D., & Tan, T. (2016). Weakly supervised large scale object localization with multiple instance learning and bag splitting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 405\u2013416.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1112_CR33","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Lin, Y., Yu, K., & Fei-Fei, L. (2012). Object-centric spatial pooling for image classification. In ECCV.","DOI":"10.1007\/978-3-642-33709-3_1"},{"key":"1112_CR34","doi-asserted-by":"crossref","unstructured":"Shi, M., & Ferrari, V. (2016). Weakly supervised object localization using size estimates. In ECCV.","DOI":"10.1007\/978-3-319-46454-1_7"},{"issue":"10","key":"1112_CR35","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1109\/TPAMI.2015.2392769","volume":"37","author":"Z Shi","year":"2015","unstructured":"Shi, Z., Hospedales, T. M., & Xiang, T. (2015). Bayesian joint modelling for object localisation in weakly labelled images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(10), 1959\u20131972.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1112_CR36","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ."},{"key":"1112_CR37","doi-asserted-by":"crossref","unstructured":"Siva, P., Russell, C., & Xiang, T. (2012). In defence of negative mining for annotating weakly labelled data. In ECCV.","DOI":"10.1007\/978-3-642-33712-3_43"},{"key":"1112_CR38","doi-asserted-by":"crossref","unstructured":"Siva, P., Russell, C., Xiang, T., & Agapito, L. (2013). Looking beyond the image: Unsupervised learning for object saliency and detection. In CVPR.","DOI":"10.1109\/CVPR.2013.416"},{"key":"1112_CR39","doi-asserted-by":"crossref","unstructured":"Siva, P., & Xiang, T. (2011). Weakly supervised object detector learning with model drift detection. In ICCV.","DOI":"10.1109\/ICCV.2011.6126261"},{"key":"1112_CR40","unstructured":"Song, H.\u00a0O., Girshick, R., Jegelka, S., Mairal, J., Harchaoui, Z., & Darrell, T. (2014a). On learning to localize objects with minimal supervision. arXiv preprint arXiv:1403.1024 ."},{"key":"1112_CR41","unstructured":"Song, H.\u00a0O., Lee, Y.\u00a0J., Jegelka, S., & Darrell, T. (2014b). Weakly-supervised discovery of visual pattern configurations. In NIPS."},{"key":"1112_CR42","unstructured":"Spitkovsky, V. I., Alshawi, H., & Jurafsky, D. (2009). Baby steps: How less is more in unsupervised dependency parsing. NIPS: Grammar Induction, Representation of Language and Language Learning."},{"key":"1112_CR43","doi-asserted-by":"crossref","unstructured":"Supancic, D., & Ramanan, J.\u00a0S. (2013). Self-paced learning for long-term tracking. In CVPR.","DOI":"10.1109\/CVPR.2013.308"},{"key":"1112_CR44","doi-asserted-by":"crossref","unstructured":"Tang, Y., Yang, Y.-B., & Gao, Y. (2012). Self-paced dictionary learning for image classification. In ACM-MM.","DOI":"10.1145\/2393347.2396324"},{"issue":"2","key":"1112_CR45","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J. R., Van De Sande, K. E., Gevers, T., & Smeulders, A. W. (2013). Selective search for object recognition. International Journal of Computer Vision, 104(2), 154\u2013171.","journal-title":"International Journal of Computer Vision"},{"key":"1112_CR46","doi-asserted-by":"crossref","unstructured":"Wang, L., Hua, G., Sukthankar, R., Xue, J., & Zheng, N. (2014a). Video object discovery and co-segmentation with extremely weak supervision. In ECCV.","DOI":"10.1007\/978-3-319-10593-2_42"},{"key":"1112_CR47","doi-asserted-by":"crossref","unstructured":"Wang, C., Ren, W., Huang, K., & Tan, T. (2014b). Weakly supervised object localization with latent category learning. In ECCV.","DOI":"10.1007\/978-3-319-10599-4_28"},{"issue":"05","key":"1112_CR48","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1142\/S0218001407005703","volume":"21","author":"X Yang","year":"2007","unstructured":"Yang, X., Song, Q., & Wang, Y. (2007). A weighted support vector machine for data classification. International Journal of Pattern Recognition and Artificial Intelligence, 21(05), 961\u2013976.","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"issue":"7","key":"1112_CR49","doi-asserted-by":"publisher","first-page":"3196","DOI":"10.1109\/TIP.2017.2694222","volume":"26","author":"X Yao","year":"2017","unstructured":"Yao, X., Han, J., Zhang, D., & Nie, F. (2017). Revisiting co-saliency detection: A novel approach based on two-stage multi-view spectral rotation co-clustering. IEEE Transactions on Image Processing, 26(7), 3196\u20133209.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"4","key":"1112_CR50","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1145\/3158674","volume":"9","author":"D Zhang","year":"2018","unstructured":"Zhang, D., Fu, H., Han, J., Borji, A., & Li, X. (2018). A review of co-saliency detection algorithms: Fundamentals, applications, and challenges. ACM Transactions on Intelligent Systems and Technology, 9(4), 38.","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"issue":"5","key":"1112_CR51","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/TPAMI.2016.2567393","volume":"39","author":"D Zhang","year":"2017","unstructured":"Zhang, D., Meng, D., & Han, J. (2017a). Co-saliency detection via a self-paced multiple-instance learning framework. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(5), 865\u2013878.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1112_CR52","unstructured":"Zhang, D., Meng, D., Zhao, L., & Han, J. (2016). Bridging saliency detection to weakly supervised object detection based on self-paced curriculum learning. In IJCAI."},{"key":"1112_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yang, L., Meng, D., Xu, D., & Han, J. (2017b). Spftn: A self-paced fine-tuning network for segmenting objects in weakly labelled videos. In CVPR.","DOI":"10.1109\/CVPR.2017.567"},{"key":"1112_CR54","doi-asserted-by":"crossref","unstructured":"Zitnick, C.\u00a0L., & Doll\u00e1r, P. (2014). Edge boxes: Locating object proposals from edges. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1112-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-018-1112-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1112-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T18:58:56Z","timestamp":1661885936000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-018-1112-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,28]]},"references-count":54,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["1112"],"URL":"https:\/\/doi.org\/10.1007\/s11263-018-1112-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,28]]},"assertion":[{"value":"24 June 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}