{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:08:01Z","timestamp":1784308081038,"version":"3.55.0"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.ins.2026.123805","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:14:00Z","timestamp":1782198840000},"page":"123805","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Knowledge annotation of multi-modal educational resources adaptable to new category discovery"],"prefix":"10.1016","volume":"755","author":[{"given":"Zeyuan","family":"Qu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3184-6805","authenticated-orcid":false,"given":"Yongjun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiakun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123805_bib0005","series-title":"Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval, SIGIR \u201903","first-page":"26","article-title":"Question classification using support vector machines","author":"Zhang","year":"2003"},{"key":"10.1016\/j.ins.2026.123805_bib0010","series-title":"Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue","first-page":"624","article-title":"Question type prediction in natural debate","author":"Kikteva","year":"2024"},{"key":"10.1016\/j.ins.2026.123805_bib0015","series-title":"2024 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","first-page":"115","article-title":"Question classification using graph convolutional network","author":"Dewi","year":"2024"},{"key":"10.1016\/j.ins.2026.123805_bib0020","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7482","article-title":"Generalized category discovery","author":"Vaze","year":"2022"},{"issue":"11","key":"10.1016\/j.ins.2026.123805_bib0025","first-page":"12527","article-title":"Generalized category discovery with decoupled prototypical network","volume":"37","author":"Wenbin","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"15","key":"10.1016\/j.ins.2026.123805_bib0030","first-page":"15365","article-title":"Unleashing the potential of model bias for generalized category discovery","volume":"39","author":"An","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.ins.2026.123805_bib0035","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Learning to discover novel visual categories via deep transfer clustering","author":"Han","year":"2019"},{"key":"10.1016\/j.ins.2026.123805_bib0040","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8360","article-title":"Discovering new intents via constrained deep adaptive clustering with cluster refinement","author":"Lin","year":"2020"},{"key":"10.1016\/j.ins.2026.123805_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15291","article-title":"Pseudo label refinery for unsupervised domain adaptation on cross-dataset 3D object detection","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ins.2026.123805_bib0050","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"132","article-title":"Deep clustering for unsupervised learning of visual features","author":"Caron","year":"2018"},{"key":"10.1016\/j.ins.2026.123805_bib0055","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"256","article-title":"New intent discovery with pre-training and contrastive learning","author":"Zhang","year":"2022"},{"issue":"4","key":"10.1016\/j.ins.2026.123805_bib0060","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MIS.2023.3283909","article-title":"New user intent discovery with robust pseudo label training and source domain joint training","volume":"38","author":"Wenbin","year":"2023","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.ins.2026.123805_bib0065","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10862","article-title":"Neighborhood contrastive learning for novel class discovery","author":"Zhong","year":"2021"},{"key":"10.1016\/j.ins.2026.123805_bib0070","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"16590","article-title":"Parametric classification for generalized category discovery: a baseline study","author":"Wen","year":"2023"},{"key":"10.1016\/j.ins.2026.123805_bib0075","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"12292","article-title":"DNA: denoised neighborhood aggregation for fine-grained category discovery","author":"Wenbin","year":"2023"},{"key":"10.1016\/j.ins.2026.123805_bib0080","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"1314","article-title":"Fine-grained category discovery under coarse-grained supervision with hierarchical weighted self-contrastive learning","author":"Wenbin","year":"2022"},{"key":"10.1016\/j.ins.2026.123805_bib0085","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"4115","article-title":"Coarse-to-fine few-shot learning for named entity recognition","author":"Ruotian","year":"2023"},{"issue":"10","key":"10.1016\/j.ins.2026.123805_bib0090","first-page":"10856","article-title":"Transfer and alignment network for generalized category discovery","volume":"38","author":"Wenbin","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.ins.2026.123805_bib0095","article-title":"Deep multimodal fusion for semantic image segmentation: a survey","author":"Zhang","year":"2021","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.ins.2026.123805_bib0100","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"3","article-title":"Learning visual question answering by bootstrapping hard attention","author":"Malinowski","year":"2018"},{"key":"10.1016\/j.ins.2026.123805_bib0105","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Bi-directional relationship inferring network for referring image segmentation","author":"Zhiwei","year":"2020"},{"key":"10.1016\/j.ins.2026.123805_bib0110","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12226","article-title":"D-vlog: multimodal vlog dataset for depression detection","volume":"vol. 36","author":"Yoon","year":"2022"},{"key":"10.1016\/j.ins.2026.123805_bib0115","series-title":"IEEE Geoscience and Remote Sensing Letters","first-page":"1","article-title":"Deep encoder-decoder networks for classification of hyperspectral and LiDAR data","author":"Hong","year":"2022"},{"key":"10.1016\/j.ins.2026.123805_bib0120","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"12427","article-title":"Transforming visual scene graphs to image captions","author":"Yang","year":"2023"},{"key":"10.1016\/j.ins.2026.123805_bib0125","first-page":"2121","article-title":"DeViSE: a deep visual-semantic embedding model","volume":"2","author":"Frome","year":"2013","journal-title":"Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123805_bib0130","series-title":"Proceedings of the 26th ACM International Conference on Multimedia, MM \u201918","first-page":"843","article-title":"Cross-modal moment localization in videos","author":"Liu","year":"2018"},{"key":"10.1016\/j.ins.2026.123805_bib0135","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.ins.2026.123805_bib0140","article-title":"Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Jiasen","year":"2019","journal-title":"Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123805_bib0145","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language (EMNLP-IJCNLP)","first-page":"5100","article-title":"LXMERT: learning cross-modality encoder representations from transformers","author":"Tan","year":"2019"},{"issue":"16","key":"10.1016\/j.ins.2026.123805_bib0150","first-page":"14365","article-title":"Discovering new intents with deep aligned clustering","volume":"35","author":"Zhang","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.ins.2026.123805_bib0155","first-page":"1135","article-title":"Few-shot generalized category discovery with retrieval-guided decision boundary enhancement","author":"Ren","year":"2025","journal-title":"ICMR \u201925"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S002002552600736X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S002002552600736X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:01:36Z","timestamp":1784307696000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S002002552600736X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":31,"alternative-id":["S002002552600736X"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123805","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Knowledge annotation of multi-modal educational resources adaptable to new category discovery","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123805","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123805"}}