{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:55:42Z","timestamp":1782312942372,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"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":["U22B2035, 62272128, 62206141, 62236009 and 12271083"],"award-info":[{"award-number":["U22B2035, 62272128, 62206141, 62236009 and 12271083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2021YFF0900500"],"award-info":[{"award-number":["2021YFF0900500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611758","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"5605-5613","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Reservoir Computing Transformer for Image-Text Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2393-9016","authenticated-orcid":false,"given":"Wenrui","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0799-440X","authenticated-orcid":false,"given":"Zhengyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3178-9772","authenticated-orcid":false,"given":"Liang-Jian","family":"Deng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5401-5676","authenticated-orcid":false,"given":"Penghong","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0111-1023","authenticated-orcid":false,"given":"Jinqiao","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_2_1","volume-title":"TPAMI","author":"Peng Liang","year":"2020","unstructured":"Liang Peng, Yang Yang, Zheng Wang, Zi Huang, and Heng Tao Shen. Mra-net: Improving vqa via multi-modal relation attention network. In TPAMI, 2020."},{"key":"e_1_3_2_1_3_1","volume-title":"CVPR","author":"Anderson Peter","year":"2018","unstructured":"Peter Anderson, Qi Wu, Damien Teney, Jake Bruce, Mark Johnson, Niko S\u00fcnderhauf, Ian Reid, Stephen Gould, and Anton Van Den Hengel. Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments. In CVPR, 2018."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2629758"},{"key":"e_1_3_2_1_6_1","volume-title":"Self-supervised video hashing with hierarchical binary autoencoder","author":"Song Jingkuan","year":"2018","unstructured":"Jingkuan Song, Hanwang Zhang, Xiangpeng Li, Lianli Gao, Meng Wang, and Richang Hong. Self-supervised video hashing with hierarchical binary autoencoder. IEEE TIP, 2018."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11276"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548138"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3396520"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249754"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3310870"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00466"},{"key":"e_1_3_2_1_20_1","volume-title":"European Conference on Computer Vision (ECCV).","author":"Chen Zhuangzhuang","unstructured":"Zhuangzhuang Chen, Jin Zhang, Pan Wang, Jie Chen, and Jianqiang Li. When active learning meets implicit semantic data augmentation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_21_1","volume":"201","author":"Li Jianqiang","unstructured":"Jianqiang Li, Zhuang-Zhuang Chen, Luxiang Huang, Min Fang, Bing Li, Xianghua Fu, Huihui Wang, and Qingguo Zhao. Automatic classification of fetal heart rate based on convolutional neural network. IEEE Internet of Things Journal, 2019.","journal-title":"Things Journal"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2962086"},{"key":"e_1_3_2_1_23_1","volume-title":"IEEE TCSVT","author":"Li Wenrui","year":"2022","unstructured":"Wenrui Li, Zhengyu Ma, Liang-Jian Deng, Xiaopeng Fan, and Yonghong Tian. Neuron-based spiking transmission and reasoning network for robust image-text retrieval. IEEE TCSVT, 2022."},{"key":"e_1_3_2_1_24_1","volume-title":"BMVC","author":"Faghri F.","year":"2018","unstructured":"F. Faghri, D.J. Fleet, J.R. Kiros, and S. Fidler. VSE: improved visual-semantic embeddings with hard negatives. In BMVC, 2018."},{"key":"e_1_3_2_1_25_1","volume-title":"NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, 2017."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"e_1_3_2_1_27_1","volume-title":"NAACL-HLT","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. Bert: Pretraining of deep bidirectional transformers for language understanding. In NAACL-HLT, 2019."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"e_1_3_2_1_29_1","volume-title":"NeurIPS","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In NeurIPS, 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data. In arXiv preprint arXiv:2001.07966","author":"Qi Di","year":"2020","unstructured":"Di Qi, Lin Su, Jia Song, Edward Cui, Taroon Bharti, and Arun Sacheti. Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data. In arXiv preprint arXiv:2001.07966, 2020."},{"key":"e_1_3_2_1_31_1","volume-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers. In arXiv preprint arXiv:2004.00849","author":"Huang Zhicheng","year":"2020","unstructured":"Zhicheng Huang, Zhaoyang Zeng, Bei Liu, Dongmei Fu, and Jianlong Fu. Pixel-bert: Aligning image pixels with text by deep multi-modal transformers. In arXiv preprint arXiv:2004.00849, 2020."},{"key":"e_1_3_2_1_32_1","volume-title":"ICLR","author":"Su Weijie","year":"2019","unstructured":"Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. Vl-bert: Pre-training of generic visual-linguistic representations. In ICLR, 2019."},{"key":"e_1_3_2_1_33_1","volume-title":"Frontiers in Neuroscience","author":"Kudithipudi Dhireesha","year":"2016","unstructured":"Dhireesha Kudithipudi, Qutaiba Saleh, Cory Merkel, James Thesing, and Bryant Wysocki. Design and analysis of a neuromemristive reservoir computing architecture for biosignal processing. Frontiers in Neuroscience, 2016."},{"key":"e_1_3_2_1_34_1","unstructured":"Herbert Jaeger. The ?echo state\" approach to analysing and training recurrent neural networks-with an erratum note. In Germany: German National Research Center for Information Technology GMD Technical Report 2001."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760407955"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.2330"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27715-5"},{"key":"e_1_3_2_1_38_1","volume-title":"Science","author":"Jaeger Herbert","year":"2004","unstructured":"Herbert Jaeger and Harald Haas. Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. In Science, 2004."},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in neural information processing systems 16: proceedings of the 2003 conference","author":"Thrun Sebastian","year":"2004","unstructured":"Sebastian Thrun, Lawrence K Saul, and Bernhard Sch\u00f6lkopf. Advances in neural information processing systems 16: proceedings of the 2003 conference. MIT press, 2004."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3001377"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5481"},{"key":"e_1_3_2_1_42_1","volume-title":"Next generation reservoir computing. Nature communications","author":"Gauthier Daniel J","year":"2021","unstructured":"Daniel J Gauthier, Erik Bollt, Aaron Griffith, and Wendson AS Barbosa. Next generation reservoir computing. Nature communications, 2021."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572844"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"e_1_3_2_1_46_1","volume-title":"IEEE TCSVT","author":"Yang Song","year":"2022","unstructured":"Song Yang, Qiang Li, Wenhui Li, Xuanya Li, and An-An Liu. Dual-level represen- tation enhancement on characteristic and context for image-text retrieval. IEEE TCSVT, 2022."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531368"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_1_52_1","volume-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","author":"Young Peter","year":"2014","unstructured":"Peter Young, Alice Lai, Micah Hodosh, and Julia Hockenmaier. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. In TACL. MIT Press, 2014."},{"key":"e_1_3_2_1_53_1","volume-title":"ECCV","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In ECCV, 2014."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859738"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747440"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611758","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:14:19Z","timestamp":1755821659000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611758"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":58,"alternative-id":["10.1145\/3581783.3611758","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611758","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}