{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T08:41:50Z","timestamp":1768812110034,"version":"3.49.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"4s","license":[{"start":{"date-parts":[[2016,11,18]],"date-time":"2016-11-18T00:00:00Z","timestamp":1479427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Ten Thousand Talent Program of China"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61522203 and 61402228"],"award-info":[{"award-number":["61522203 and 61402228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"973 Program of China","award":["2014CB347600"],"award-info":[{"award-number":["2014CB347600"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2016,11,18]]},"abstract":"<jats:p>In recent years, deep neural networks have been successfully applied to model visual concepts and have achieved competitive performance on many tasks. Despite their impressive performance, traditional deep networks are subjected to the decayed performance under the condition of lacking sufficient training data. This problem becomes extremely severe for deep networks trained on a very small dataset, making them overfitting by capturing nonessential or noisy information in the training set. Toward this end, we propose a novel generalized deep transfer networks (DTNs), capable of transferring label information across heterogeneous domains, textual domain to visual domain. The proposed framework has the ability to adequately mitigate the problem of insufficient training images by bringing in rich labels from the textual domain. Specifically, to share the labels between two domains, we build parameter- and representation-shared layers. They are able to generate domain-specific and shared interdomain features, making this architecture flexible and powerful in capturing complex information from different domains jointly. To evaluate the proposed method, we release a new dataset extended from NUS-WIDE at http:\/\/imag.njust.edu.cn\/NUS-WIDE-128.html. Experimental results on this dataset show the superior performance of the proposed DTNs compared to existing state-of-the-art methods.<\/jats:p>","DOI":"10.1145\/2998574","type":"journal-article","created":{"date-parts":[[2016,11,18]],"date-time":"2016-11-18T15:40:54Z","timestamp":1479483654000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":129,"title":["Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains"],"prefix":"10.1145","volume":"12","author":[{"given":"Jinhui","family":"Tang","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo-Jun","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,11,18]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Jimmy Ba and Brendan Frey. 2013. Adaptive dropout for training deep neural networks. In Advances in Neural Information Processing Systems 26 (NIPS\u201913).   Jimmy Ba and Brendan Frey. 2013. Adaptive dropout for training deep neural networks. In Advances in Neural Information Processing Systems 26 (NIPS\u201913)."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201912)","author":"Bengio Yoshua","year":"2012"},{"key":"e_1_2_1_4_1","unstructured":"Yoshua Bengio Aaron C. Courville and Pascal Vincent. 2012. Unsupervised feature learning and deep learning: A review and new perspectives. arXiv:1206.5538v1.  Yoshua Bengio Aaron C. Courville and Pascal Vincent. 2012. Unsupervised feature learning and deep learning: A review and new perspectives. arXiv:1206.5538v1."},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201912)","author":"Chen Minmin"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.92"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201912)","author":"Duan Lixin"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.12.020"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2015.2446438"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.313"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201911)","author":"Glorot Xavier","year":"2011"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487860"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631296"},{"key":"e_1_2_1_20_1","unstructured":"Alexander Kalmanovich and Gal Chechik. 2014. Gradual training of deep denoising auto encoders. arXiv:1412.6257.  Alexander Kalmanovich and Gal Chechik. 2014. Gradual training of deep denoising auto encoders. arXiv:1412.6257."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.243"},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of the International Conference on Systems, Man, and Cybernetics (SMC\u201914)","author":"Kandaswamy Chetak"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_2_1_24_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012"},{"key":"e_1_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. Nature 521 7553 436--444.  Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. Nature 521 7553 436--444.","DOI":"10.1038\/nature14539"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2400461"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477035"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.183"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201911)","author":"Ngiam Jiquan"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.95"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654987"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963449"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273592"},{"key":"e_1_2_1_35_1","unstructured":"Antti Rasmus Harri Valpola and Tapani Raiko. 2015. Lateral connections in denoising autoencoders support supervised learning. arXiv:1504.08215.  Antti Rasmus Harri Valpola and Tapani Raiko. 2015. Lateral connections in denoising autoencoders support supervised learning. arXiv:1504.08215."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393437"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS\u201909)","author":"Salakhutdinov Ruslan"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"e_1_2_1_40_1","unstructured":"Richard Socher Milind Ganjoo Christopher D. Manning and Andrew Ng. 2013. Zero-shot learning through cross-modal transfer. In Advances in Neural Information Processing Systems 26 (NIPS\u201913).   Richard Socher Milind Ganjoo Christopher D. Manning and Andrew Ng. 2013. Zero-shot learning through cross-modal transfer. In Advances in Neural Information Processing Systems 26 (NIPS\u201913)."},{"key":"e_1_2_1_41_1","unstructured":"Kihyuk Sohn Wenling Shang and Honglak Lee. 2014. Improved multimodal deep learning with variation of information. In Advances in Neural Information Processing Systems 27 (NIPS\u201914).   Kihyuk Sohn Wenling Shang and Honglak Lee. 2014. Improved multimodal deep learning with variation of information. In Advances in Neural Information Processing Systems 27 (NIPS\u201914)."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0390-0"},{"key":"e_1_2_1_43_1","unstructured":"Nitish Srivastava and Ruslan Salakhutdinov. 2012. Multimodal learning with deep Boltzmann machines. In Advances in Neural Information Processing Systems 25 (NIPS\u201912).   Nitish Srivastava and Ruslan Salakhutdinov. 2012. Multimodal learning with deep Boltzmann machines. In Advances in Neural Information Processing Systems 25 (NIPS\u201912)."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1899412.1899418"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2476660"},{"key":"e_1_2_1_46_1","first-page":"1","article-title":"Tri-clustered tensor completion for social-aware image tag refinement","volume":"99","author":"Tang Jinhui","year":"2016","journal-title":"IEEE Transaction on Pattern Analysis and Machine Intelligence PP"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953039"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_2_1_50_1","unstructured":"Wen Wang Zhen Cui Hong Chang Shiguang Shan and Xilin Chen. 2014a. Deeply coupled auto-encoder networks for cross-view classification. arXiv:1402.2031.  Wen Wang Zhen Cui Hong Chang Shiguang Shan and Xilin Chen. 2014a. Deeply coupled auto-encoder networks for cross-view classification. arXiv:1402.2031."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732296.2732301"},{"key":"e_1_2_1_52_1","volume-title":"Neural Networks: Tricks of the Trade","author":"Weston Jason"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654914"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2700286"},{"key":"e_1_2_1_55_1","volume-title":"Shih-Fu Chang, and Shengjin Wang.","author":"Zhang Xu","year":"2015"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/423581"},{"key":"e_1_2_1_57_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201911)","author":"Zhu Yin","year":"2011"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2998574","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2998574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:50:35Z","timestamp":1750218635000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2998574"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,18]]},"references-count":57,"journal-issue":{"issue":"4s","published-print":{"date-parts":[[2016,11,18]]}},"alternative-id":["10.1145\/2998574"],"URL":"https:\/\/doi.org\/10.1145\/2998574","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11,18]]},"assertion":[{"value":"2016-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2016-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2016-11-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}