{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:45:39Z","timestamp":1777941939725,"version":"3.51.4"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Central Universities under Grant","award":["2019CDYGZD003"],"award-info":[{"award-number":["2019CDYGZD003"]}]},{"name":"Chongqing Technology Innovation and Application Development Project","award":["CSTB2023TIAD-KPX0050"],"award-info":[{"award-number":["CSTB2023TIAD-KPX0050"]}]},{"name":"Chongqing Technology Innovation and Application Development Project","award":["CSTB2023TIAD-KPX0050"],"award-info":[{"award-number":["CSTB2023TIAD-KPX0050"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s00371-024-03723-6","type":"journal-article","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T07:01:01Z","timestamp":1733814061000},"page":"5311-5322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multimodal fusion and knowledge distillation for improved anomaly detection"],"prefix":"10.1007","volume":"41","author":[{"given":"Meichen","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Chai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaixiong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Ao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"issue":"1","key":"3723_CR1","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/s11633-023-1459-z","volume":"21","author":"J Liu","year":"2024","unstructured":"Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., Jin, Y.: Deep industrial image anomaly detection: a survey. Mach. Intell. Res. 21(1), 104\u2013135 (2024)","journal-title":"Mach. Intell. Res."},{"issue":"2","key":"3723_CR2","doi-asserted-by":"publisher","first-page":"2477","DOI":"10.1109\/TII.2023.3292904","volume":"20","author":"Y Guo","year":"2024","unstructured":"Guo, Y., Jiang, M., Huang, Q., Cheng, Y., Gong, J.: MLDFR: A Multilevel Features Restoration Method Based on Damaged Images for Anomaly Detection and Localization. IEEE Trans. Ind. Inf. 20(2), 2477\u20132486 (2024). https:\/\/doi.org\/10.1109\/TII.2023.3292904","journal-title":"IEEE Trans. Ind. Inf."},{"key":"3723_CR3","doi-asserted-by":"crossref","unstructured":"Zhou, K., Xiao, Y., Yang, J., Cheng, J., Liu, W., Luo, W., Gu, Z., Liu, J., Gao, S.: Encoding structure-texture relation with p-net for anomaly detection in retinal images. In: Proceedings of the European Conference on Computer Vision, pp. 360\u2013377 (2020)","DOI":"10.1007\/978-3-030-58565-5_22"},{"issue":"1","key":"3723_CR4","doi-asserted-by":"publisher","first-page":"3242","DOI":"10.1038\/s41467-021-23458-5","volume":"12","author":"L Dai","year":"2021","unstructured":"Dai, L., Wu, L., Li, H., Cai, C., Wu, Q., Kong, H., Liu, R., Wang, X., Hou, X., Liu, Y.: A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12(1), 3242 (2021)","journal-title":"Nat. Commun."},{"issue":"5","key":"3723_CR5","doi-asserted-by":"publisher","first-page":"2814","DOI":"10.1109\/TCSVT.2021.3099943","volume":"32","author":"H Li","year":"2021","unstructured":"Li, H., Dong, N., Yu, Z., Tao, D., Qi, G.: Triple adversarial learning and multi-view imaginative reasoning for unsupervised domain adaptation person re-identification. IEEE Trans. Circuits Syst. Video Technol. 32(5), 2814\u20132830 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3723_CR6","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TIFS.2020.3036800","volume":"16","author":"H Li","year":"2020","unstructured":"Li, H., Chen, Y., Tao, D., Yu, Z., Qi, G.: Attribute-aligned domain-invariant feature learning for unsupervised domain adaptation person re-identification. IEEE Trans. Inf. Forensics Secur. 16, 1480\u20131494 (2020)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"5","key":"3723_CR7","doi-asserted-by":"publisher","first-page":"1625","DOI":"10.1007\/s11263-023-01948-x","volume":"132","author":"H Li","year":"2024","unstructured":"Li, H., Liu, J., Zhang, Y., Liu, Y.: A deep learning framework for infrared and visible image fusion without strict registration. Int. J. Comput. Vision 132(5), 1625\u20131644 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"3723_CR8","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.inffus.2023.02.011","volume":"95","author":"H Li","year":"2023","unstructured":"Li, H., Zhao, J., Li, J., Yu, Z., Lu, G.: Feature dynamic alignment and refinement for infrared-visible image fusion: translation robust fusion. Inf. Fusion 95, 26\u201341 (2023)","journal-title":"Inf. Fusion"},{"key":"3723_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105139","volume":"149","author":"S Paulraj","year":"2024","unstructured":"Paulraj, S., Vairavasundaram, S.: M2vad: multiview multimodality transformer-based weakly supervised video anomaly detection. Image Vis. Comput. 149, 105139 (2024)","journal-title":"Image Vis. Comput."},{"issue":"6","key":"3723_CR10","doi-asserted-by":"publisher","first-page":"4023","DOI":"10.1007\/s00371-024-03412-4","volume":"40","author":"Y Zang","year":"2024","unstructured":"Zang, Y., Lu, A.K., Li, B., Hu, W.J.: Revisiting segmentation-guided denoising student-teacher in anomaly detection. Vis. Comput. 40(6), 4023\u20134038 (2024). https:\/\/doi.org\/10.1007\/s00371-024-03412-4","journal-title":"Vis. Comput."},{"issue":"2","key":"3723_CR11","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1038\/s41591-023-02702-z","volume":"30","author":"L Dai","year":"2024","unstructured":"Dai, L., Sheng, B., Chen, T., Wu, Q., Liu, R., Cai, C., Wu, L., Yang, D., Hamzah, H., Liu, Y.: A deep learning system for predicting time to progression of diabetic retinopathy. Nat. Med. 30(2), 584\u2013594 (2024)","journal-title":"Nat. Med."},{"key":"3723_CR12","doi-asserted-by":"crossref","unstructured":"Roth, K., Pemula, L., Zepeda, J., Sch\u00f6lkopf, B., Brox, T., Gehler, P.: Towards total recall in industrial anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14318\u201314328 (2021)","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"3723_CR13","doi-asserted-by":"publisher","unstructured":"Hyun, J., Kim, S., Jeon, G., Kim, S.H., Bae, K., Kang, B.J.: Reconpatch : Contrastive patch representation learning for industrial anomaly detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2024). https:\/\/doi.org\/10.1109\/WACV57701.2024.00205.","DOI":"10.1109\/WACV57701.2024.00205."},{"key":"3723_CR14","doi-asserted-by":"crossref","unstructured":"He, H., Zhang, J., Chen, H., Chen, X., Li, Z., Chen, X., Wang, Y., Wang, C., Xie, L.: A diffusion-based framework for multi-class anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 8472\u20138480 (2024)","DOI":"10.1609\/aaai.v38i8.28690"},{"key":"3723_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xu, M., Zhou, X.: Realnet: A feature selection network with realistic synthetic anomaly for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16699\u201316708 (2024)","DOI":"10.1109\/CVPR52733.2024.01580"},{"key":"3723_CR16","first-page":"4571","volume":"35","author":"Z You","year":"2022","unstructured":"You, Z., Cui, L., Shen, Y., Yang, K., Lu, X., Zheng, Y., Le, X.: A unified model for multi-class anomaly detection. Adv. Neural. Inf. Process. Syst. 35, 4571\u20134584 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3723_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03281-x","author":"YC Chen","year":"2024","unstructured":"Chen, Y.C., Chen, B., Xian, W.Z., Wang, J.J., Huang, Y., Chen, M.: Lgfdr: local and global feature denoising reconstruction for unsupervised anomaly detection. Vis. Comput. (2024). https:\/\/doi.org\/10.1007\/s00371-024-03281-x","journal-title":"Vis. Comput."},{"key":"3723_CR18","doi-asserted-by":"crossref","unstructured":"Gudovskiy, D., Ishizaka, S., Kozuka, K.: Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 98\u2013107 (2022)","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"3723_CR19","doi-asserted-by":"crossref","unstructured":"Lei, J., Hu, X., Wang, Y., Liu, D.: Pyramidflow: High-resolution defect contrastive localization using pyramid normalizing flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14143\u201314152 (2023)","DOI":"10.1109\/CVPR52729.2023.01359"},{"key":"3723_CR20","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"issue":"9","key":"3723_CR21","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"issue":"6","key":"3723_CR22","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/j.vrih.2023.06.003","volume":"5","author":"M Wang","year":"2023","unstructured":"Wang, M., Meng, M., Liu, J., Wu, J.: Learning adequate alignment and interaction for cross-modal retrieval. Virtual Real. Intell. Hardw. 5(6), 509\u2013522 (2023)","journal-title":"Virtual Real. Intell. Hardw."},{"key":"3723_CR23","doi-asserted-by":"crossref","unstructured":"Jeong, J., Zou, Y., Kim, T., Zhang, D., Ravichandran, A., Dabeer, O.: Winclip: Zero-\/few-shot anomaly classification and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19606\u201319616 (2023)","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"3723_CR24","unstructured":"Zhou, Q., Pang, G., Tian, Y., He, S., Chen, J.: Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection. In: Proceedings of the International Conference on Learning Representations (2024)"},{"key":"3723_CR25","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, Z., Tan, X., Chen, C., Qu, Y., Xie, Y., Ma, L.: Promptad: Learning prompts with only normal samples for few-shot anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16838\u201316848 (2024)","DOI":"10.1109\/CVPR52733.2024.01594"},{"key":"3723_CR26","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhu, B., Zhu, G., Chen, Y., Tang, M., Wang, J.: Anomalygpt: Detecting industrial anomalies using large vision-language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 1932\u20131940 (2024)","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"3723_CR27","doi-asserted-by":"crossref","unstructured":"Hu, C., Chen, K., Shao, H.: A semantic-enhanced method based on deep svdd for pixel-wise anomaly detection. In: Proceedings of the IEEE International Conference on Multimedia and Expo, pp. 1\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428370"},{"key":"3723_CR28","doi-asserted-by":"crossref","unstructured":"Yi, J., Yoon, S.: Patch svdd: Patch-level svdd for anomaly detection and segmentation. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69544-6_23"},{"issue":"8","key":"3723_CR29","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2021","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.P.: Bagfn: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499\u20134513 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"3723_CR30","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/JSTSP.2020.2987728","volume":"14","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Yang, Z., He, X., Deng, L.: Multimodal intelligence: representation learning, information fusion, and applications. IEEE J. Sel. Top. Signal Process. 14(3), 478\u2013493 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"3723_CR31","unstructured":"Kim, J.-H., On, K.-W., Lim, W., Kim, J., Ha, J.-W., Zhang, B.-T.: Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325 (2016)"},{"key":"3723_CR32","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"3723_CR33","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: Mutan: Multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"3723_CR34","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Thome, N., Cord, M.: Block: Bilinear superdiagonal fusion for visual question answering and visual relationship detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8102\u20138109 (2019)","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"3723_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"issue":"1","key":"3723_CR36","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/TAI.2022.3160418","volume":"4","author":"A Mishra","year":"2022","unstructured":"Mishra, A., Anand, A., Guha, P.: Dual attention and question categorization-based visual question answering. IEEE Trans. Artif. Intell. 4(1), 81\u201391 (2022)","journal-title":"IEEE Trans. Artif. Intell."},{"key":"3723_CR37","unstructured":"Kim, J.-H., Jun, J., Zhang, B.-T.: Bilinear attention networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"3723_CR38","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"3723_CR39","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"key":"3723_CR40","first-page":"2383","volume":"2022","author":"W Dai","year":"2022","unstructured":"Dai, W., Hou, L., Shang, L., Jiang, X., Liu, Q., Fung, P.: Enabling multimodal generation on clip via vision-language knowledge distillation. Findings of the Association for Computational Linguistics: ACL 2022, 2383\u20132395 (2022)","journal-title":"Findings of the Association for Computational Linguistics: ACL"},{"key":"3723_CR41","doi-asserted-by":"crossref","unstructured":"Zou, Y., Jeong, J., Pemula, L., Zhang, D., Dabeer, O.: Spot-the-difference self-supervised pre-training for anomaly detection and segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 392\u2013408 (2022)","DOI":"10.1007\/978-3-031-20056-4_23"},{"key":"3723_CR42","doi-asserted-by":"crossref","unstructured":"Defard, T., Setkov, A., Loesch, A., Audigier, R.: Padim: a patch distribution modeling framework for anomaly detection and localization. In: Proceedings of the International Conference on Pattern Recognition, pp. 475\u2013489 (2021)","DOI":"10.1007\/978-3-030-68799-1_35"},{"issue":"3","key":"3723_CR43","doi-asserted-by":"publisher","first-page":"12499","DOI":"10.1111\/exsy.12499","volume":"37","author":"S Ding","year":"2020","unstructured":"Ding, S., Hu, S., Pan, J., Li, X., Li, G., Liu, X.: A homogeneous ensemble method for predicting gastric cancer based on gastroscopy reports. Expert. Syst. 37(3), 12499 (2020)","journal-title":"Expert. Syst."},{"key":"3723_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102007","volume":"70","author":"D Jha","year":"2021","unstructured":"Jha, D., Ali, S., Hicks, S., Thambawita, V., Borgli, H., Smedsrud, P.H., Lange, T., Pogorelov, K., Wang, X., Harzig, P.: A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging. Med. Image Anal. 70, 102007 (2021)","journal-title":"Med. Image Anal."},{"key":"#cr-split#-3723_CR45.1","unstructured":"Chen, X., Han, Y., Zhang, J.: A zero-\/fewshot anomaly classification and segmentation method for cvpr 2023 vand workshop challenge tracks 1 and 2: 1st place on zero-shot ad and 4th place on few-shot ad. 2"},{"key":"#cr-split#-3723_CR45.2","unstructured":"(4) (2023), arXiv preprint arXiv:2305.17382"},{"key":"3723_CR46","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03723-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03723-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03723-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T08:47:02Z","timestamp":1747385222000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03723-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":47,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["3723"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03723-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"9 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that this paper is original and has no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}