{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:35:51Z","timestamp":1740101751125,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094565","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Divcon: Learning Concept Sequences for Semantically Diverse Image Captioning"],"prefix":"10.1109","author":[{"given":"Yue","family":"Zheng","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya-Li","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref12","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Int Conference on Machine Learning"},{"key":"ref15","first-page":"91","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems-Volume 1"},{"key":"ref14","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Int Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","first-page":"2957","article-title":"Diverse image captioning via grouptalk","author":"wang","year":"0","journal-title":"IJCAI"},{"key":"ref1","first-page":"5758","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space","author":"wang","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref17","article-title":"The curious case of neural text degeneration","author":"holtzman","year":"2019","journal-title":"arXiv preprint arXiv 1904 09099"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"ref24","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref25","article-title":"Analysis of diversity-accuracy tradeoff in image captioning","author":"luo","year":"2020","journal-title":"arXiv preprint arXiv 2002 11040"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref22","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2014","journal-title":"arXiv preprint arXiv 1412 6632"},{"key":"ref21","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref7","first-page":"211","article-title":"Comprehensive image captioning via scene graph decomposition","author":"zhong","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00436"},{"key":"ref3","article-title":"Diverse beam search: Decoding diverse solutions from neural sequence models","author":"vijayakumar","year":"2016","journal-title":"arXiv preprint arXiv 1610 02984"},{"key":"ref6","article-title":"Diverse image captioning with context-object split latent spaces","author":"mahajan","year":"2020","journal-title":"arXiv preprint arXiv 2011 00177"},{"article-title":"Variational structured semantic inference for diverse image captioning","year":"2019","author":"chen","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094565.pdf?arnumber=10094565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:57:09Z","timestamp":1699901829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094565","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}