{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:13:40Z","timestamp":1772554420690,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191139","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["TRMER: Transformer-Based End to End Printed Mathematical Expression Recognition"],"prefix":"10.1109","author":[{"given":"Zhaokun","family":"Zhou","sequence":"first","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaijian","family":"Ji","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Weng","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuesheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref35","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00834"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref36","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref11","article-title":"How much position information do convolutional neural networks encode?","author":"islam","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"ref32","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10740"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3168361"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref18","first-page":"12299","article-title":"Pretrained image processing transformer","author":"chen","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref24","first-page":"980","article-title":"Image-to-markup generation with coarse-to-fine attention","author":"deng","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/9789812830968_0021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15937-4_50"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"ref20","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"chu","year":"2021","journal-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2001.953767"},{"key":"ref21","article-title":"Conditional positional encodings for vision transformers","author":"chu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume":"34","author":"yang","year":"2021","journal-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref29","first-page":"1","article-title":"Delving deeper into anti-aliasing in convnets","author":"zou","year":"2022","journal-title":"International Journal of Computer Vision"},{"key":"ref8","first-page":"2286","article-title":"Convit: Improving vision transformers with soft convolutional inductive biases","author":"st\u00e9phane d'ascoli","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_42"},{"key":"ref4","article-title":"Edsl: An encoder-decoder architecture with symbol-level features for printed mathematical expression recognition","author":"fu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","first-page":"436","article-title":"Syntax-directed recognition of hand-printed two-dimensional mathematics","author":"robert","year":"1967","journal-title":"Symposium on Interactive Systems for Experimental Applied Mathematics Proceedings of the Association for Computing Machinery Inc Symposium"},{"key":"ref6","volume":"30","author":"vaswani","year":"2017","journal-title":"Attention is all you need"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","location":"Gold Coast, Australia","start":{"date-parts":[[2023,6,18]]},"end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191139.pdf?arnumber=10191139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:44:22Z","timestamp":1692639862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191139","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}