{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:50Z","timestamp":1774419410769,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887902","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["HiE-VL: A Large Vision-Language Model with Hierarchical Adapter for Handwritten Mathematical Expression Recognition"],"prefix":"10.1109","author":[{"given":"Hong-Yu","family":"Guo","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}]},{"given":"Fei","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On-line recognition of handwritten mathematical expressions based on stroke-based stochastic context-free grammar","volume-title":"Tenth international workshop on frontiers in handwriting recognition","author":"Yamamoto"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.09.023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.09.013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2001.953891"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00293"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16399"},{"key":"ref7","first-page":"980","article-title":"Image-to-markup generation with coarse-to-fine attention","volume-title":"International Conference on Machine Learning","author":"Deng"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01291-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_23"},{"key":"ref10","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref11","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref13","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref15","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref17","article-title":"Exploring ocr capabilities of gpt-4v (ision): A quantitative and in-depth evaluation","author":"Shi","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_12"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00451"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref21","article-title":"Textmonkey: An ocr-free large multimodal model for understanding document","author":"Liu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref24","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2014.138"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icfhr.2016.0116"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00247"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR2020.2020.00047"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.09.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546031"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956214"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110155"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86331-9_37"},{"key":"ref34","first-page":"11076","article-title":"A tree-structured decoder for image-to-markup generation","volume-title":"International Conference on Machine Learning","author":"Zhang"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887902.pdf?arnumber=10887902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:44Z","timestamp":1774416164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887902\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887902","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}