{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:31:04Z","timestamp":1778167864312,"version":"3.51.4"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414636","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"4170-4174","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Stacked Learning with Semantic-Associated Attention for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Xiao","sequence":"first","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,School of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref12","article-title":"Learning to count objects in natural images for visual question answering","author":"zhang","year":"2018","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref13","article-title":"Multi-modality latent interaction network for visual question answering","author":"gao","year":"2019","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref16","article-title":"VL-BERT: pre-training of generic visual-linguistic representations","author":"su","year":"0"},{"key":"ref17","article-title":"Self-critical reasoning for robust visual question answering","author":"wu","year":"2019","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","first-page":"273","article-title":"Chain of reasoning for visual question answering","author":"wu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.229"},{"key":"ref5","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31865-1_25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414636.pdf?arnumber=9414636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:18:18Z","timestamp":1659485898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414636","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}