{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T20:07:21Z","timestamp":1787170041339,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant 62172263 and Grant U1836216"],"award-info":[{"award-number":["Grant 62172263 and Grant U1836216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Shandong, China","award":["Grant ZR2020YQ47 and Grant ZR2019QF002"],"award-info":[{"award-number":["Grant ZR2020YQ47 and Grant ZR2019QF002"]}]},{"name":"Youth Innovation Project of Shandong Universities, China","award":["Grant 2019KJN040"],"award-info":[{"award-number":["Grant 2019KJN040"]}]},{"name":"Major Fundamental Research Project of Shandong, China","award":["Grant ZR2019ZD03"],"award-info":[{"award-number":["Grant ZR2019ZD03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531947","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T11:12:08Z","timestamp":1657192328000},"page":"982-991","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Bit-aware Semantic Transformer Hashing for Multi-modal Retrieval"],"prefix":"10.1145","author":[{"given":"Wentao","family":"Tan","sequence":"first","affiliation":[{"name":"Shandong Normal University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shandong Normal University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weili","family":"Guan","sequence":"additional","affiliation":[{"name":"Monash University, Clayton, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjing","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shandong Artificial Intelligence Institute, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_2_1","volume-title":"TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval. arXiv preprint arXiv:2105.01823","author":"Chen Yongbiao","year":"2021","unstructured":"Yongbiao Chen , Sheng Zhang , Fangxin Liu , Zhigang Chang , Mang Ye , and Zhengwei Qi. 2021. TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval. arXiv preprint arXiv:2105.01823 ( 2021 ). Yongbiao Chen, Sheng Zhang, Fangxin Liu, Zhigang Chang, Mang Ye, and Zhengwei Qi. 2021. TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval. arXiv preprint arXiv:2105.01823 (2021)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186 . Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the International Conference on Learning Representations .","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy , Lucas Beyer , Alexander Kolesnikov , Dirk Weissenborn , Xiaohua Zhai , Thomas Unterthiner , Mostafa Dehghani , Matthias Minderer , Georg Heigold , Sylvain Gelly , Jakob Uszkoreit , and Neil Houlsby . 2021 . An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale . In Proceedings of the International Conference on Learning Representations . Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proceedings of the International Conference on Learning Representations ."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_2_7_1","volume-title":"Long Short-Term Memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber . 1997. Long Short-Term Memory. Neural computation , Vol. 9 , 8 ( 1997 ), 1735--1780. Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long Short-Term Memory. Neural computation , Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings of the ACM SIGMM International Conference on Multimedia Information Retrieval. 527--536","author":"Huiskes Mark J.","unstructured":"Mark J. Huiskes , Bart Thomee , and Michael S. Lew . 2010. New trends and ideas in visual concept detection: the MIR flickr retrieval evaluation initiative . In Proceedings of the ACM SIGMM International Conference on Multimedia Information Retrieval. 527--536 . Mark J. Huiskes, Bart Thomee, and Michael S. Lew. 2010. New trends and ideas in visual concept detection: the MIR flickr retrieval evaluation initiative. In Proceedings of the ACM SIGMM International Conference on Multimedia Information Retrieval. 527--536."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of International Conference on Learning Representations .","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization . In Proceedings of International Conference on Learning Representations . Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In Proceedings of International Conference on Learning Representations ."},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the International Conference on Learning Representations .","author":"Thomas","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks . In Proceedings of the International Conference on Learning Representations . Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of the International Conference on Learning Representations ."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01334"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the European Conference on Computer Vision. 740--755","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin , Michael Maire , Serge J. Belongie , James Hays , Pietro Perona , Deva Ramanan , Piotr Doll\u00e1 r, and C. Lawrence Zitnick . 2014. Microsoft COCO: Common Objects in Context . In Proceedings of the European Conference on Computer Vision. 740--755 . Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1 r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Proceedings of the European Conference on Computer Vision. 740--755."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2390975"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10221-y"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401086"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396337"},{"key":"e_1_3_2_2_19_1","volume-title":"Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030","author":"Liu Ze","year":"2021","unstructured":"Ze Liu , Yutong Lin , Yue Cao , Han Hu , Yixuan Wei , Zheng Zhang , Stephen Lin , and Baining Guo . 2021. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 ( 2021 ). Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350999"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947358"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475598"},{"key":"e_1_3_2_2_23_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018).  Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2789887"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178119"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806342"},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of International Conference on Learning Representations .","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman . 2015 . Very Deep Convolutional Networks for Large-Scale Image Recognition . In Proceedings of International Conference on Learning Representations . Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of International Conference on Learning Representations ."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11276"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2271746"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the International Conference on Learning Representations .","author":"Su Weijie","year":"2020","unstructured":"Weijie Su , Xizhou Zhu , Yue Cao , Bin Li , Lewei Lu , Furu Wei , and Jifeng Dai . 2020 . VL-BERT: Pre-training of Generic Visual-Linguistic Representations . In Proceedings of the International Conference on Learning Representations . Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In Proceedings of the International Conference on Learning Representations ."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017 . Attention is All you Need . In Proceedings of the Advances in Neural Information Processing Systems. 5998--6008 . Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proceedings of the Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078981"},{"key":"e_1_3_2_2_38_1","volume-title":"Le","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang , Zihang Dai , Yiming Yang , Jaime G. Carbonell , Ruslan Salakhutdinov , and Quoc V . Le . 2019 . XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Proceedings of the Advances in Neural Information Processing Systems . 5754--5764. Zhilin Yang, Zihang Dai, Yiming Yang, Jaime G. Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. 2019. XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Proceedings of the Advances in Neural Information Processing Systems . 5754--5764."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2771332"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037456"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2913388"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609610"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2883970"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.2974065"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531947","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T14:10:19Z","timestamp":1750169419000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531947"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":45,"alternative-id":["10.1145\/3477495.3531947","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531947","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}