{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T04:09:22Z","timestamp":1727842162381},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687402","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval"],"prefix":"10.1109","author":[{"given":"Rukai","family":"Wei","sequence":"first","affiliation":[{"name":"HUST,Wuhan National Laboratory for Optoelectronics,Wuhan,China"}]},{"given":"Heng","family":"Cui","sequence":"additional","affiliation":[{"name":"HUST,School of Software Engineering,Wuhan,China"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"HUST,School of Computer Science and Technology,Wuhan,China"}]},{"given":"Yanzhao","family":"Xie","sequence":"additional","affiliation":[{"name":"GZU,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Yufeng","family":"Hou","sequence":"additional","affiliation":[{"name":"HUST,School of Computer Science and Technology,Wuhan,China"}]},{"given":"Ke","family":"Zhou","sequence":"additional","affiliation":[{"name":"HUST,Wuhan National Laboratory for Optoelectronics,Wuhan,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16592"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177356"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00030"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00343"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00312"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.267"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11263"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548431"},{"key":"ref10","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00147"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29621"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00791"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448182"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref19","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref20","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res"},{"key":"ref22","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25373"},{"key":"ref25","article-title":"Contrastive masked autoencoders are stronger vision learners","author":"Huang","year":"2022","journal-title":"CoRR"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687402.pdf?arnumber=10687402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:11:39Z","timestamp":1727763099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687402","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}