{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:43:54Z","timestamp":1787017434927,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462924","type":"proceedings-article","created":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T22:41:54Z","timestamp":1626043314000},"page":"1146-1156","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":47,"title":["Heterogeneous Attention Network for Effective and Efficient Cross-modal Retrieval"],"prefix":"10.1145","author":[{"given":"Tan","family":"Yu","sequence":"first","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Fei","sequence":"additional","affiliation":[{"name":"Baidu Research, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371844"},{"key":"e_1_3_2_1_3_1","volume-title":"NIPS workshop: Machine learning for Web search .","author":"Chapelle Olivier","year":"2007","unstructured":"Olivier Chapelle, Quoc Le, and Alex Smola. 2007. Large margin optimization of ranking measures. In NIPS workshop: Machine learning for Web search ."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"e_1_3_2_1_5_1","volume-title":"On the Properties of Neural Machine Translation: Encoder--Decoder Approaches. Syntax, Semantics and Structure in Statistical Translation","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart van Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the Properties of Neural Machine Translation: Encoder--Decoder Approaches. Syntax, Semantics and Structure in Statistical Translation (2014), 103."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","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 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). Minneapolis, MN, 4171--4186."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. VSE+: Improving Visual-Semantic Embeddings with Hard Negatives. In Proceedings of the British Machine Vision Conference (BMVC). Newcastle, UK."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330651"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.285"},{"key":"e_1_3_2_1_10_1","unstructured":"Zhe Gan Yen-Chun Chen Linjie Li Chen Zhu Yu Cheng and Jingjing Liu. 2020. Large-Scale Adversarial Training for Vision-and-Language Representation Learning. In Advances in Neural Information Processing Systems (NeurIPS). virtual."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). Online.","author":"Hong Weixiang","year":"2021","unstructured":"Weixiang Hong, Qingpei Guo, Wei Zhang, Jingdong Chen, and Wei Chu. 2021. Neural Networks for Information Retrieval. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). Online."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3082062"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_19_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems (NIPS). Lake Tahoe, NV, 1106--1114."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the Eleventh ACM International Conference on Multimedia (ACMMM)","author":"Li Dongge","unstructured":"Dongge Li, Nevenka Dimitrova, Mingkun Li, and Ishwar K. Sethi. 2003. Multimedia content processing through cross-modal association. In Proceedings of the Eleventh ACM International Conference on Multimedia (ACMMM). Berkeley, CA, 604--611."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_1_23_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 13th European Conference on Computer Vision (ECCV), Part V","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 13th European Conference on Computer Vision (ECCV), Part V. Zurich, Switzerland, 740--755."},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS).","author":"Lu Jiasen","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Advances in Neural Information Processing Systems (NeurIPS). Vancouver, Canada, 13--23."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"e_1_3_2_1_28_1","volume-title":"Univilm: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353","author":"Luo Huaishao","year":"2020","unstructured":"Huaishao Luo, Lei Ji, Botian Shi, Haoyang Huang, Nan Duan, Tianrui Li, Xilin Chen, and Ming Zhou. 2020. Univilm: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"e_1_3_2_1_30_1","volume-title":"Berg","author":"Ordonez Vicente","year":"2011","unstructured":"Vicente Ordonez, Girish Kulkarni, and Tamara L. Berg. 2011. Im2Text: Describing Images Using 1 Million Captioned Photographs. In Advances in Neural Information Processing Systems (NIPS). Granada, Spain, 1143--1151."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia.","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 8th International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371830"},{"key":"e_1_3_2_1_40_1","volume-title":"Advances in Neural Information Processing Systems (NIPS).","author":"Vaswani Ashish","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 Advances in Neural Information Processing Systems (NIPS). Long Beach, CA, 5998--6008."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457236"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_46_1","volume-title":"2020 a. ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph. arXiv preprint arXiv:2006.16934","author":"Yu Fei","year":"2020","unstructured":"Fei Yu, Jiji Tang, Weichong Yin, Yu Sun, Hao Tian, Hua Wu, and Haifeng Wang. 2020 a. ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph. arXiv preprint arXiv:2006.16934 (2020)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449830"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00225"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403297"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159730"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 3rd Conference on Machine Learning and Systems (MLSys)","author":"Zhao Weijie","year":"2020","unstructured":"Weijie Zhao, Deping Xie, Ronglai Jia, Yulei Qian, Ruiquan Ding, Mingming Sun, and Ping Li. 2020. Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems. In Proceedings of the 3rd Conference on Machine Learning and Systems (MLSys). Austin, TX."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358045"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462924","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:18:20Z","timestamp":1750177100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462924"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":52,"alternative-id":["10.1145\/3404835.3462924","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462924","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}