{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:03:35Z","timestamp":1765357415738,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108100"],"award-info":[{"award-number":["2020AAA0108100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971343, 62088102"],"award-info":[{"award-number":["61971343, 62088102"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3592025","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"2194-2198","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Multi-grained Representation Learning for Cross-modal Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3882-7959","authenticated-orcid":false,"given":"Shengwei","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7785-6913","authenticated-orcid":false,"given":"Linhai","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7295-3308","authenticated-orcid":false,"given":"Yuying","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-0596","authenticated-orcid":false,"given":"Shaoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979989"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_2_3_1","volume-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv preprint arXiv:2109.04290","author":"Cheng Xing","year":"2021","unstructured":"Xing Cheng, Hezheng Lin, Xiangyu Wu, Fan Yang, and Dong Shen. 2021. Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv preprint arXiv:2109.04290 (2021)."},{"key":"e_1_3_2_2_4_1","volume-title":"Christophe De Vleeschouwer, and Marc Van Droogenbroeck","author":"Deli\u00e8ge Adrien","year":"2021","unstructured":"Adrien Deli\u00e8ge, Maxime Istasse, Ashwani Kumar, Christophe De Vleeschouwer, and Marc Van Droogenbroeck. 2021. Ordinal pooling. arXiv preprint arXiv:2109.01561 (2021)."},{"key":"e_1_3_2_2_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_10_1","volume-title":"International Conference on Machine Learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning. PMLR, 4904--4916."},{"key":"e_1_3_2_2_11_1","volume-title":"A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188","author":"Kalchbrenner Nal","year":"2014","unstructured":"Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014)."},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Kim Chris Dongjoo","year":"2019","unstructured":"Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. Audiocaps: Generating captions for audios in the wild. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 119--132."},{"key":"e_1_3_2_2_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_14_1","volume-title":"Audio retrieval with natural language queries: A benchmark study","author":"Koepke A Sophia","year":"2022","unstructured":"A Sophia Koepke, Andreea-Maria Oncescu, Joao Henriques, Zeynep Akata, and Samuel Albanie. 2022. Audio retrieval with natural language queries: A benchmark study. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_2_17_1","volume-title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval. arXiv preprint arXiv:2207.07852","author":"Liu Yuqi","year":"2022","unstructured":"Yuqi Liu, Pengfei Xiong, Luhui Xu, Shengming Cao, and Qin Jin. 2022. TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval. arXiv preprint arXiv:2207.07852 (2022)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_2_20_1","volume-title":"On Metric Learning for Audio-Text Cross-Modal Retrieval. arXiv preprint arXiv:2203.15537","author":"Mei Xinhao","year":"2022","unstructured":"Xinhao Mei, Xubo Liu, Jianyuan Sun, Mark D Plumbley, and Wenwu Wang. 2022. On Metric Learning for Audio-Text Cross-Modal Retrieval. arXiv preprint arXiv:2203.15537 (2022)."},{"key":"e_1_3_2_2_21_1","volume-title":"Z.","author":"Oncescu A.-M.","year":"2021","unstructured":"A.-M. Oncescu, A.S. Koepke, J. Henriques, and Albanie S. Akata, Z. 2021. Audio Retrieval with Natural Language Queries. In INTERSPEECH."},{"key":"e_1_3_2_2_22_1","volume-title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation. arXiv preprint arXiv:2211.06687","author":"Wu Yusong","year":"2022","unstructured":"Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Taylor Berg-Kirkpatrick, and Shlomo Dubnov. 2022. Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation. arXiv preprint arXiv:2211.06687 (2022)."},{"key":"e_1_3_2_2_23_1","volume-title":"Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783","author":"Yao Lewei","year":"2021","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021. Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)."},{"key":"e_1_3_2_2_24_1","volume-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. arXiv preprint arXiv:2111.08276","author":"Zeng Yan","year":"2021","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2021. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. arXiv preprint arXiv:2111.08276 (2021)."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Taipei Taiwan","acronym":"SIGIR '23"},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592025","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3592025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:49Z","timestamp":1750178269000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":24,"alternative-id":["10.1145\/3539618.3592025","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3592025","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}