{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:43:48Z","timestamp":1760420628339,"version":"build-2065373602"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"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":[[2025,9,22]]},"DOI":"10.1109\/icnp65844.2025.11192381","type":"proceedings-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:38:54Z","timestamp":1760377134000},"page":"1-15","source":"Crossref","is-referenced-by-count":0,"title":["Towards Automatic Network Diagram Comprehension"],"prefix":"10.1109","author":[{"given":"Yanyu","family":"Ren","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukai","family":"Miao","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xizheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Bai","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"CAS,ICT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Long","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2023","key":"ref1","article-title":"Overview of network topology and connectivity for Azure - Cloud Adoption Framework"},{"key":"ref2","first-page":"22","article-title":"Inter-domain Source Address Validation (SAVNET) Architecture","volume-title":"Internet Engineering Task Force, Internet Draft draft-wu-savnet-interdomain-architecture-02","author":"Wu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672268"},{"key":"ref5","article-title":"Network Monitoring Software by ManageEngine OpManager"},{"article-title":"Gpt-4o system card","year":"2024","author":"Hurst","key":"ref6"},{"year":"2021","key":"ref7","article-title":"YOLOv5: A state-of-the-art real-time object detection system"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref9"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","year":"2025","author":"Guo","key":"ref11"},{"article-title":"Cogvlm: Visual expert for pretrained language models","year":"2023","author":"Wang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01354"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"article-title":"An empirical study of netops capability of pre-trained large language models","year":"2023","author":"Miao","key":"ref17"},{"key":"ref18","article-title":"Cisco Certified Network Associate"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref22","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.416"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref27","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","year":"2023","author":"Bai","key":"ref28"},{"article-title":"Can multimodal llms do visual temporal understanding and reasoning? the answer is no!","year":"2025","author":"Imam","key":"ref29"},{"year":"2023","key":"ref30","article-title":"Gemini: A family of highly capable multimodal models"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868466"},{"key":"ref33","first-page":"469","article-title":"A general approach to network configuration analysis","volume-title":"12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15)","author":"Fogel"},{"article-title":"The faiss library","year":"2024","author":"Douze","key":"ref34"},{"key":"ref35","article-title":"Method and means for recognizing complex patterns","volume-title":"uS Patent","author":"Hough","year":"1962"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"article-title":"Ultralytics YOLO","year":"2023","author":"Jocher","key":"ref37"},{"key":"ref38","article-title":"PP-OCR: A practical ultra lightweight OCR system","volume-title":"CoRR","author":"Du","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00323"},{"issue":"4","key":"ref40","first-page":"26","article-title":"Evaluating user cognition of network diagrams","volume-title":"Visual Informatics","volume":"5","author":"Chen","year":"2021"},{"article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","year":"2024","author":"Wu","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100047"},{"article-title":"Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning","year":"2017","author":"Rajpurkar","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Berlin50680.2020.9352180"},{"article-title":"Improving image generation with better captions","year":"2023","author":"Betker","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3569219.3569352"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2015.2411412"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"article-title":"Dataset of architectural diagrams (images) used for recovering model nodes and their relations","year":"2014","author":"Rago","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.25080\/tcwv9851"},{"key":"ref53","article-title":"Drawing graphs with graphviz","volume-title":"Technical report","author":"Gansner","year":"2009"},{"article-title":"Facexbench: Evaluating multimodal llms on face understanding","year":"2025","author":"Narayan","key":"ref54"}],"event":{"name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","start":{"date-parts":[[2025,9,22]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2025,9,25]]}},"container-title":["2025 IEEE 33rd International Conference on Network Protocols (ICNP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11192357\/11192322\/11192381.pdf?arnumber=11192381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:08:26Z","timestamp":1760418506000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11192381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icnp65844.2025.11192381","relation":{},"subject":[],"published":{"date-parts":[[2025,9,22]]}}}