[{"date_updated":"2024-10-14T11:10:00Z","scopus_import":"1","author":[{"full_name":"Kang, Peipei","last_name":"Kang","first_name":"Peipei"},{"first_name":"Zehang","last_name":"Lin","full_name":"Lin, Zehang"},{"last_name":"Yang","first_name":"Zhenguo","full_name":"Yang, Zhenguo"},{"first_name":"Alexander","last_name":"Bronstein","id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","full_name":"Bronstein, Alexander","orcid":"0000-0001-9699-8730"},{"first_name":"Qing","last_name":"Li","full_name":"Li, Qing"},{"full_name":"Liu, Wenyin","first_name":"Wenyin","last_name":"Liu"}],"abstract":[{"lang":"eng","text":"Existing cross-modal hashing methods ignore the informative multimodal joint information and cannot fully exploit the semantic labels. In this paper, we propose a deep fused two-step cross-modal hashing (DFTH) framework with multiple semantic supervision. In the first step, DFTH learns unified hash codes for instances by a fusion network. Semantic label and similarity reconstruction have been introduced to acquire binary codes that are informative, discriminative and semantic similarity preserving. In the second step, two modality-specific hash networks are learned under the supervision of common hash codes reconstruction, label reconstruction, and intra-modal and inter-modal semantic similarity reconstruction. The modality-specific hash networks can generate semantic preserving binary codes for out-of-sample queries. To deal with the vanishing gradients of binarization, continuous differentiable tanh is introduced to approximate the discrete sign function, making the networks able to back-propagate by automatic gradient computation. Extensive experiments on MIRFlickr25K and NUS-WIDE show the superiority of DFTH over state-of-the-art methods."}],"language":[{"iso":"eng"}],"type":"journal_article","quality_controlled":"1","status":"public","citation":{"short":"P. Kang, Z. Lin, Z. Yang, A.M. Bronstein, Q. Li, W. Liu, Multimedia Tools and Applications 81 (2022) 15653–15670.","chicago":"Kang, Peipei, Zehang Lin, Zhenguo Yang, Alex M. Bronstein, Qing Li, and Wenyin Liu. “Deep Fused Two-Step Cross-Modal Hashing with Multiple Semantic Supervision.” <i>Multimedia Tools and Applications</i>. Springer Nature, 2022. <a href=\"https://doi.org/10.1007/s11042-022-12187-6\">https://doi.org/10.1007/s11042-022-12187-6</a>.","mla":"Kang, Peipei, et al. “Deep Fused Two-Step Cross-Modal Hashing with Multiple Semantic Supervision.” <i>Multimedia Tools and Applications</i>, vol. 81, no. 11, Springer Nature, 2022, pp. 15653–70, doi:<a href=\"https://doi.org/10.1007/s11042-022-12187-6\">10.1007/s11042-022-12187-6</a>.","apa":"Kang, P., Lin, Z., Yang, Z., Bronstein, A. M., Li, Q., &#38; Liu, W. (2022). Deep fused two-step cross-modal hashing with multiple semantic supervision. <i>Multimedia Tools and Applications</i>. Springer Nature. <a href=\"https://doi.org/10.1007/s11042-022-12187-6\">https://doi.org/10.1007/s11042-022-12187-6</a>","ista":"Kang P, Lin Z, Yang Z, Bronstein AM, Li Q, Liu W. 2022. Deep fused two-step cross-modal hashing with multiple semantic supervision. Multimedia Tools and Applications. 81(11), 15653–15670.","ieee":"P. Kang, Z. Lin, Z. Yang, A. M. Bronstein, Q. Li, and W. Liu, “Deep fused two-step cross-modal hashing with multiple semantic supervision,” <i>Multimedia Tools and Applications</i>, vol. 81, no. 11. Springer Nature, pp. 15653–15670, 2022.","ama":"Kang P, Lin Z, Yang Z, Bronstein AM, Li Q, Liu W. Deep fused two-step cross-modal hashing with multiple semantic supervision. <i>Multimedia Tools and Applications</i>. 2022;81(11):15653-15670. doi:<a href=\"https://doi.org/10.1007/s11042-022-12187-6\">10.1007/s11042-022-12187-6</a>"},"oa_version":"None","date_published":"2022-05-01T00:00:00Z","month":"05","extern":"1","publisher":"Springer Nature","intvolume":"        81","date_created":"2024-10-08T12:55:04Z","year":"2022","publication":"Multimedia Tools and Applications","publication_status":"published","fulldoi":"https://doi.org/10.1007/s11042-022-12187-6","page":"15653-15670","day":"01","publication_identifier":{"eissn":["1573-7721"],"issn":["1380-7501"]},"title":"Deep fused two-step cross-modal hashing with multiple semantic supervision","_id":"18227","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","volume":81,"article_processing_charge":"No","article_type":"original","issue":"11","doi":"10.1007/s11042-022-12187-6"}]