{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T13:09:09Z","timestamp":1768396149495,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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":[[2025,9,21]]},"DOI":"10.1109\/mmsp64401.2025.11324237","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:55:15Z","timestamp":1768337715000},"page":"352-357","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Document Layout Analysis through Text Clustering via Multi-Modal Graph Convolution Networks"],"prefix":"10.1109","author":[{"given":"Wenxi","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China"}]},{"given":"Chenyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commerce,AI Business,Hangzhou,China"}]},{"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"China Telecom,Shanghai,China"}]},{"given":"Liting","family":"Zhou","sequence":"additional","affiliation":[{"name":"Dublin City University,Dublin,Ireland"}]},{"given":"Cathal","family":"Gurrin","sequence":"additional","affiliation":[{"name":"Dublin City University,Dublin,Ireland"}]},{"given":"Yuchen","family":"Guo","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR2020.2020.00017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01453"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3355610"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539043"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2017.142","article-title":"Fast cnn-based document layout analysis","volume-title":"ICCVW","author":"Augusto Borges Oliveira"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01293"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99978-4_31"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00121"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01338"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref16","article-title":"Angle-optimized text embeddings","author":"Li","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref18","article-title":"YOLOv5 by Ultralytics","author":"Jocher","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41676-7_18"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref21","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref22","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","author":"Li","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref29","article-title":"Solov2: Dynamic and fast instance segmentation","author":"Wang","year":"2020","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Deformable {detr}: Deformable transformers for end-to-end object detection","volume-title":"ICLR","author":"Zhu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref32","article-title":"Istr: End-to-end instance segmentation with transformers","author":"Hu","year":"2021"},{"key":"ref33","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin"},{"key":"ref34","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"}],"event":{"name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","location":"Beijing, China","start":{"date-parts":[[2025,9,21]]},"end":{"date-parts":[[2025,9,23]]}},"container-title":["2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11324077\/11324018\/11324237.pdf?arnumber=11324237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:52:32Z","timestamp":1768377152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11324237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/mmsp64401.2025.11324237","relation":{},"subject":[],"published":{"date-parts":[[2025,9,21]]}}}