{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,29]],"date-time":"2024-12-29T05:05:37Z","timestamp":1735448737068,"version":"3.32.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007750","name":"National Cheng Kung University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/apccas62602.2024.10808400","type":"proceedings-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:09:25Z","timestamp":1735326565000},"page":"641-645","source":"Crossref","is-referenced-by-count":0,"title":["OCR is All you need: Importing Multi-Modality into Image-based Defect Classification System"],"prefix":"10.1109","author":[{"given":"Chih-Chung","family":"Hsu","sequence":"first","affiliation":[{"name":"Institute of Data Science National Cheng Kung University,Tainan,Taiwan"}]},{"given":"Chia-Ming","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Data Science National Cheng Kung University,Tainan,Taiwan"}]},{"given":"Po-Tsun","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Data Science National Cheng Kung University,Tainan,Taiwan"}]},{"given":"Chun-Hung","family":"Sun","sequence":"additional","affiliation":[{"name":"Corporate R&D Advanced Semiconductor Engineering Group,Kaoshuing,Taiwan"}]},{"given":"Kuang-Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"Corporate R&D Advanced Semiconductor Engineering Group,Kaoshuing,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref3","first-page":"11474","article-title":"Xiang Bai: Real-time Scene Text Detection with Differentiable Binarization","volume-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","author":"Liao"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2646371"},{"key":"ref5","article-title":"Sequence to Sequence Learning with Neural Networks","author":"Sutskever","year":"2014","journal-title":"arXiv preprint, arXiv:1507.05717v1"},{"key":"ref6","first-page":"9694","article-title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems (NeurlPS)"},{"key":"ref7","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International conference on machine learning (ICML)","author":"Radford"},{"key":"ref8","first-page":"12888","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","volume-title":"International conference on machine learning (ICML)","author":"Li"},{"key":"ref9","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Li","year":"2023","journal-title":"arXiv preprint, arXiv:2301.12597"},{"key":"ref10","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Dai","year":"2023","journal-title":"arXiv preprint, arXiv:2305.06500"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01476-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63830-6_12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295070"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref16","article-title":"CatBoost: unbiased boosting with categorical features","author":"Prokhorenkova","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"volume-title":"Random forests, Ensemble machine learning: Methods and applications","year":"2012","author":"Cutler","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2307\/2699986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems (NeurlPS)"},{"key":"ref23","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint, arXiv:1409.1556"},{"key":"ref24","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning (ICML)","author":"Tan"},{"key":"ref25","article-title":"Ilya Sutskever: Zero-Shot Text-to-Image Generation","author":"Ramesh","year":"2021","journal-title":"arXiv preprint, arXiv:2102.12092"},{"key":"ref26","article-title":"GridMask Data Augmentation","author":"Chen","year":"2020","journal-title":"arXiv preprint, arXiv:2001.04086v2"}],"event":{"name":"2024 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","start":{"date-parts":[[2024,11,7]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2024,11,9]]}},"container-title":["2024 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10808178\/10808208\/10808400.pdf?arnumber=10808400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T06:22:15Z","timestamp":1735366935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10808400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/apccas62602.2024.10808400","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}