{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:03:58Z","timestamp":1743134638038,"version":"3.40.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"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":[[2025,1,11]]},"DOI":"10.1109\/icce63647.2025.10930135","type":"proceedings-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:16:58Z","timestamp":1743041818000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset"],"prefix":"10.1109","author":[{"given":"Chih-Chung","family":"Hsu","sequence":"first","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Ming","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Tsun","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Jun","family":"Kang","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Hung","family":"Sun","sequence":"additional","affiliation":[{"name":"Corporate R&D, Advanced Semiconductor Engineering Group,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuang-Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"Corporate R&D, Advanced Semiconductor Engineering Group,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app11167657"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1115\/1.4049535"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00189"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s40684-021-00343-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01878-w"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01145"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01325"},{"volume-title":"Mixed supervision for surface-defect detection: from weakly to fully supervised learning","year":"2021","author":"Jakob","key":"ref8"},{"volume-title":"Segmentation-based deep-learning approach for surface-defect detection","year":"2020","author":"Domen","key":"ref9"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1145\/3571600.3571607","article-title":"Convolutional ensembling based few-shot defect detection technique","volume-title":"Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing","author":"Karmakar"},{"key":"ref11","article-title":"Few-shot defect detection using feature enhancement and image generation for manufacturing quality inspection","volume-title":"Applied Intelligence","author":"Yu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00460"},{"key":"ref13","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 (NeurIPS)"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International conference on machine learning (ICML)","author":"Radford","year":"2021"},{"key":"ref15","first-page":"12888","article-title":"Blip: Bootstrapping language-image pretraining for unified vision-language understanding and generation","volume-title":"Proceedings of the International conference on machine learning (ICML)","author":"Li","year":"2022"},{"key":"ref16","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","volume":"arXiv:2301.12597","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","volume":"arXiv:2305.06500","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Llama: Open and efficient foundation language models","volume":"arXiv:2302.13971","author":"Hugo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Llama 2: Open foundation and fine-tuned chat models","volume":"arXiv:2307.09288","author":"T","year":"2023","journal-title":"arXiv preprint"},{"volume-title":"CnOCR","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00678"},{"key":"ref22","article-title":"Contrastive learning with hard negative samples","volume-title":"International Conference on Learning Representations","author":"Robinson","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref25","article-title":"Training data-efficient image transformers and distillation through attention","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Touvron","year":"2021"},{"key":"ref26","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the International conference on machine learning (ICML)","author":"Tan","year":"2019"},{"key":"ref27","article-title":"Defect classification and detection using a multitask deep one-class cnn","author":"Cootes","year":"2021","journal-title":"IEEE Transactions on Automation Science and Engineering (TASE)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","volume":"arXiv:1810.04805","author":"Jacob","year":"2018","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Loshchilov","year":"2019"}],"event":{"name":"2025 IEEE International Conference on Consumer Electronics (ICCE)","start":{"date-parts":[[2025,1,11]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2025,1,14]]}},"container-title":["2025 IEEE International Conference on Consumer Electronics (ICCE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10929765\/10929768\/10930135.pdf?arnumber=10930135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:54:54Z","timestamp":1743062094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10930135\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,11]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icce63647.2025.10930135","relation":{},"subject":[],"published":{"date-parts":[[2025,1,11]]}}}