{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:10:59Z","timestamp":1775243459837,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012458","type":"print"},{"value":"9783030012465","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01246-5_25","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:14:56Z","timestamp":1538756096000},"page":"415-432","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":87,"title":["A Modulation Module for Multi-task Learning with Applications in Image Retrieval"],"prefix":"10.1007","author":[{"given":"Xiangyun","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Haoxiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaohui","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"25_CR1","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1735\u20131742. IEEE (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.322"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.243"},{"issue":"1","key":"25_CR7","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2011","unstructured":"Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117\u2013128 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Jou, B., Chang, S.F.: Deep cross residual learning for multitask visual recognition. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 998\u20131007. ACM (2016)","DOI":"10.1145\/2964284.2964309"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Kokkinos, I.: Ubernet: training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.579"},{"key":"25_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Lin, K., Yang, H.F., Hsiao, J.H., Chen, C.S.: Deep learning of binary hash codes for fast image retrieval. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2015","DOI":"10.1109\/CVPRW.2015.7301269"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.126"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3994\u20134003 (2016)","DOI":"10.1109\/CVPR.2016.433"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Pirsiavash, H., Ko\u0161eck\u00e1, J.: Joint semantic segmentation and depth estimation with deep convolutional networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 611\u2013619. IEEE (2016)","DOI":"10.1109\/3DV.2016.69"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., Poirier, H.: Large-scale image retrieval with compressed fisher vectors. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3384\u20133391. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383172"},{"key":"25_CR18","unstructured":"Ranjan, R., Patel, V.M., Chellappa, R.: Hyperface: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. arXiv preprint arXiv:1603.01249 (2016)"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Ranjan, R., Sankaranarayanan, S., Castillo, C.D., Chellappa, R.: An all-in-one convolutional neural network for face analysis. In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), pp. 17\u201324. IEEE (2017)","DOI":"10.1109\/FG.2017.137"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Rothe, R., Timofte, R., Van Gool, L.: Dex: deep expectation of apparent age from a single image. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 10\u201315 (2015)","DOI":"10.1109\/ICCVW.2015.41"},{"issue":"2\u20133","key":"25_CR21","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1023\/A:1007649029923","volume":"39","author":"RE Schapire","year":"2000","unstructured":"Schapire, R.E., Singer, Y.: Boostexter: a boosting-based system for text categorization. Mach. Learn. 39(2\u20133), 135\u2013168 (2000)","journal-title":"Mach. Learn."},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"25_CR23","unstructured":"Schultz, M., Joachims, T.: Learning a distance metric from relative comparisons. In: Advances in Neural Information Processing Systems, pp. 41\u201348 (2004)"},{"key":"25_CR24","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Shen, X., Lin, Z., Brandt, J., Avidan, S., Wu, Y.: Object retrieval and localization with spatially-constrained similarity measure and k-NN re-ranking. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3013\u20133020. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248031"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Veit, A., Belongie, S., Karaletsos, T.: Conditional similarity networks. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.193"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Wan, J., et al.: Deep learning for content-based image retrieval: a comprehensive study. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 157\u2013166. ACM (2014)","DOI":"10.1145\/2647868.2654948"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Wang, J., Kumar, S., Chang, S.F.: Semi-supervised hashing for scalable image retrieval. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3424\u20133431. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539994"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: Towards unified depth and semantic prediction from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2800\u20132809 (2015)","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"25_CR30","unstructured":"Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10, 207\u2013244 (2009)"},{"key":"25_CR31","unstructured":"Xing, E.P., Jordan, M.I., Russell, S.J., Ng, A.Y.: Distance metric learning with application to clustering with side-information. In: Advances in Neural Information Processing Systems, pp. 521\u2013528 (2003)"},{"key":"25_CR32","unstructured":"Yang, Y., Hospedales, T.M.: Deep multi-task representation learning: a tensor factorisation approach. CoRR abs\/1605.06391 (2016)"},{"key":"25_CR33","unstructured":"Yin, X., Liu, X.: Multi-task convolutional neural network for face recognition. arXiv preprint arXiv:1702.04710 (2017)"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Yu, A., Grauman, K.: Fine-grained visual comparisons with local learning. In: Computer Vision and Pattern Recognition (CVPR), June 2014","DOI":"10.1109\/CVPR.2014.32"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Yu, A., Grauman, K.: Semantic jitter: dense supervision for visual comparisons via synthetic images. In: International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.594"},{"key":"25_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"issue":"10","key":"25_CR37","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499\u20131503 (2016)","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01246-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:36:54Z","timestamp":1775241414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01246-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012458","9783030012465"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01246-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}