{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T01:35:29Z","timestamp":1747445729557,"version":"3.28.0"},"reference-count":21,"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\/icassp39728.2021.9414074","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"3605-3609","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Re-Balancing Network with Gate Mechanism for Long-Tailed Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Hongyu","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Ruifang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Han","family":"Fang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Ximing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]}],"member":"263","reference":[{"article-title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","year":"2016","author":"krishna","key":"ref10"},{"article-title":"Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge","year":"2017","author":"teney","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref13","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/122"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/586"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_2"},{"article-title":"Learning to Count Objects in Natural Images for Visual Question Answering","year":"2018","author":"zhang","key":"ref17"},{"article-title":"Beyond Bilinear: Generalized Multi-modal Factorized High-order Pooling for Visual Question Answering","year":"2017","author":"yu","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref3","article-title":"Multimodal residual learning for visual qa","author":"kim","year":"2016","journal-title":"arXiv Computer Vision and Pattern Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"journal-title":"Kendall’s Advanced Theory of Statistics","year":"1987","author":"kendall","key":"ref8"},{"key":"ref7","first-page":"6850","article-title":"Aligning visual regions and textual concepts for semantic-grounded image representations","author":"liu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref1","article-title":"Making the v in vqa matter: Elevating the role of image understanding in visual question answering","author":"goyal","year":"2016","journal-title":"arXiv Computer Vision and Pattern Recognition"},{"key":"ref9","first-page":"91","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","volume":"2015","author":"ren","year":"2015"},{"article-title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","year":"2018","author":"tang","key":"ref20"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1609\/aaai.v34i01.5338","article-title":"Re-attention for visual question answering","volume":"34","author":"guo","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09414074.pdf?arnumber=9414074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:19:12Z","timestamp":1659471552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414074","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}