{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:51:11Z","timestamp":1772301071386,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956247","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1471-1477","source":"Crossref","is-referenced-by-count":8,"title":["CAT: Re-Conv Attention in Transformer for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Haotian","family":"Zhang","sequence":"first","affiliation":[{"name":"Inner Mongolia University,Hohhot,China"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,Hohhot,China"}]}],"member":"263","reference":[{"key":"ref33","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref10","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Lite transformer with long-short range attention","author":"wu","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref16","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"krishna","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref19","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019"},{"key":"ref28","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref6","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref7","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"In Adva nces in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref9","article-title":"An Improved Attention for Visual Question Answering","author":"rahman","year":"2020"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","article-title":"Long-Term Recurrent Convolutional Networks for Visual Recognition and Description","volume":"39","author":"donahue","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref20","first-page":"13","article-title":"ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413078"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref23","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956247.pdf?arnumber=9956247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:06:05Z","timestamp":1671480365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956247","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}