{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T19:00:35Z","timestamp":1758394835500,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"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":[[2021,12]]},"DOI":"10.1145\/3469877.3490601","type":"proceedings-article","created":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T18:27:21Z","timestamp":1641839241000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Hierarchical Composition Learning for Composed Query Image Retrieval"],"prefix":"10.1145","author":[{"given":"Yahui","family":"Xu","sequence":"first","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Bin","sequence":"additional","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,1,10]]},"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":"10.1109\/TCYB.2018.2831447"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018110"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","volume-title":"British Machine Vision Conference. 12","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri , David\u00a0 J. Fleet , Jamie\u00a0Ryan Kiros , and Sanja Fidler . 2018 . VSE++: Improving Visual-Semantic Embeddings with Hard Negatives . In British Machine Vision Conference. 12 . Fartash Faghri, David\u00a0J. Fleet, Jamie\u00a0Ryan Kiros, and Sanja Fidler. 2018. VSE++: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference. 12."},{"key":"e_1_3_2_1_7_1","volume-title":"Multi-Order Adversarial Representation Learning for Composed Query Image Retrieval. In International Conference on Acoustics, Speech and Signal Processing. 1685\u20131689","author":"Fu Zhixiao","year":"2021","unstructured":"Zhixiao Fu , Xinyuan Chen , Jianfeng Dong , and Shouling Ji . 2021 . Multi-Order Adversarial Representation Learning for Composed Query Image Retrieval. In International Conference on Acoustics, Speech and Signal Processing. 1685\u20131689 . Zhixiao Fu, Xinyuan Chen, Jianfeng Dong, and Shouling Ji. 2021. Multi-Order Adversarial Representation Learning for Composed Query Image Retrieval. In International Conference on Acoustics, Speech and Signal Processing. 1685\u20131689."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019306"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475184"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2941284"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890144"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2749147"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"e_1_3_2_1_18_1","unstructured":"Jin-Hwa Kim Sang-Woo Lee Dong-Hyun Kwak Min-Oh Heo Jeonghee Kim JungWoo Ha and Byoung-Tak Zhang. 2016. Multimodal Residual Learning for Visual QA. In Advances in Neural Information Processing Systems. 361\u2013369.  Jin-Hwa Kim Sang-Woo Lee Dong-Hyun Kwak Min-Oh Heo Jeonghee Kim JungWoo Ha and Byoung-Tak Zhang. 2016. Multimodal Residual Learning for Visual QA. In Advances in Neural Information Processing Systems. 361\u2013369."},{"volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations.","author":"P.","key":"e_1_3_2_1_19_1","unstructured":"Diederik\u00a0 P. Kingma and Jimmy Ba. 2015 . Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations. Diederik\u00a0P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","unstructured":"Thomas\u00a0N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907(2016).  Thomas\u00a0N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907(2016)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"e_1_3_2_1_22_1","volume-title":"Mra-net: Improving vqa via multi-modal relation attention network","author":"Peng Liang","year":"2020","unstructured":"Liang Peng , Yang Yang , Zheng Wang , Zi Huang , and Heng\u00a0Tao Shen . 2020 . Mra-net: Improving vqa via multi-modal relation attention network . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2020). Liang Peng, Yang Yang, Zheng Wang, Zi Huang, and Heng\u00a0Tao Shen. 2020. Mra-net: Improving vqa via multi-modal relation attention network. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 3942\u20133951","author":"Perez Ethan","year":"2018","unstructured":"Ethan Perez , Florian Strub , Harm de Vries , Vincent Dumoulin , and Aaron\u00a0 C. Courville . 2018 . FiLM: Visual Reasoning with a General Conditioning Layer . In Proceedings of the AAAI Conference on Artificial Intelligence. 3942\u20133951 . Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, and Aaron\u00a0C. Courville. 2018. FiLM: Visual Reasoning with a General Conditioning Layer. In Proceedings of the AAAI Conference on Artificial Intelligence. 3942\u20133951."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_26_1","unstructured":"Adam Santoro David Raposo David G.\u00a0T. Barrett Mateusz Malinowski Razvan Pascanu Peter\u00a0W. Battaglia and Tim Lillicrap. 2017. A simple neural network module for relational reasoning. In Advances in Neural Information Processing Systems.4967\u20134976.  Adam Santoro David Raposo David G.\u00a0T. Barrett Mateusz Malinowski Razvan Pascanu Peter\u00a0W. Battaglia and Tim Lillicrap. 2017. A simple neural network module for relational reasoning. In Advances in Neural Information Processing Systems.4967\u20134976."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123345"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2970050"},{"key":"e_1_3_2_1_29_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems. 5998\u20136008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356059"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3418546"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019425"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413917"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331198"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01248"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"e_1_3_2_1_45_1","unstructured":"Wengang Zhou Houqiang Li and Qi Tian. 2017. Recent advance in content-based image retrieval: A literature survey. arXiv preprint arXiv:1706.06064(2017).  Wengang Zhou Houqiang Li and Qi Tian. 2017. Recent advance in content-based image retrieval: A literature survey. arXiv preprint arXiv:1706.06064(2017)."}],"event":{"name":"MMAsia '21: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Gold Coast Australia","acronym":"MMAsia '21"},"container-title":["ACM Multimedia Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469877.3490601","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3469877.3490601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:16Z","timestamp":1750188616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469877.3490601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":45,"alternative-id":["10.1145\/3469877.3490601","10.1145\/3469877"],"URL":"https:\/\/doi.org\/10.1145\/3469877.3490601","relation":{},"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"2022-01-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}