{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:05:46Z","timestamp":1760598346220,"version":"3.44.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3"],"award-info":[{"award-number":["NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3","NSTC-112-2628-E-002-033-MY4; NSTC-113-2634-F-002-001-MBK; NSTC-112-2221-E-A49-089-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Center of Data Intelligence: Technologies, Applications, and Systems, National Taiwan University","award":["114L900901\/114L900902\/114L900903"],"award-info":[{"award-number":["114L900901\/114L900902\/114L900903"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00530-025-01797-3","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T18:28:20Z","timestamp":1747938500000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Swapped logit distillation via bi-level teacher alignment"],"prefix":"10.1007","volume":"31","author":[{"given":"Stephen Ekaputra","family":"Limantoro","sequence":"first","affiliation":[]},{"given":"Jhe-Hao","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Chih-Yu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yi-Lung","family":"Tsai","sequence":"additional","affiliation":[]},{"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[]},{"given":"Ching-Chun","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"1797_CR1","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1797_CR2","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"1797_CR3","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"1797_CR4","doi-asserted-by":"crossref","unstructured":"Huang, Y.-X., Liu, H.-I., Shuai, H.-H., Cheng, W.-H.: Dq-detr: Detr with dynamic query for tiny object detection. In: European Conference on Computer Vision, pp. 290\u2013305 (2025). Springer","DOI":"10.1007\/978-3-031-73116-7_17"},{"key":"1797_CR5","doi-asserted-by":"crossref","unstructured":"Sio, C.H., Ma, Y.-J., Shuai, H.-H., Chen, J.-C., Cheng, W.-H.: S2siamfc: Self-supervised fully convolutional siamese network for visual tracking. In: ACM Int. Conf. Multimedia, pp. 1948\u20131957 (2020)","DOI":"10.1145\/3394171.3413611"},{"issue":"4","key":"1797_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447239","volume":"54","author":"W-H Cheng","year":"2021","unstructured":"Cheng, W.-H., Song, S., Chen, C.-Y., Hidayati, S.C., Liu, J.: Fashion meets computer vision: A survey. ACM Comput. Surv. 54(4), 1\u201341 (2021)","journal-title":"ACM Comput. Surv."},{"key":"1797_CR7","doi-asserted-by":"crossref","unstructured":"Hsieh, C.-W., Chen, C.-Y., Chou, C.-L., Shuai, H.-H., Liu, J., Cheng, W.-H.: Fashionon: Semantic-guided image-based virtual try-on with detailed human and clothing information. In: ACM Int. Conf. Multimedia, pp. 275\u2013283 (2019)","DOI":"10.1145\/3343031.3351075"},{"key":"1797_CR8","doi-asserted-by":"crossref","unstructured":"Hidayati, S.C., Hsu, C.-C., Chang, Y.-T., Hua, K.-L., Fu, J., Cheng, W.-H.: What dress fits me best? fashion recommendation on the clothing style for personal body shape. In: ACM Int. Conf. Multimedia, pp. 438\u2013446 (2018)","DOI":"10.1145\/3240508.3240546"},{"key":"1797_CR9","doi-asserted-by":"crossref","unstructured":"Hsiao, Y.-S., Sanchez-Riera, J., Lim, T., Hua, K.-L., Cheng, W.-H.: Lared: A large rgb-d extensible hand gesture dataset. In: Proceedings of the 5th ACM Multimedia Systems Conference, pp. 53\u201358 (2014)","DOI":"10.1145\/2557642.2563669"},{"key":"1797_CR10","unstructured":"Kapitanov, A., Kvanchiani, K., Nagaev, A., Kraynov, R., Makhliarchuk, A.: Hagrid\u2013hand gesture recognition image dataset. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4572\u20134581 (2024)"},{"key":"1797_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13640-016-0151-4","volume":"2016","author":"FS Abousaleh","year":"2016","unstructured":"Abousaleh, F.S., Lim, T., Cheng, W.-H., Yu, N.-H., Hossain, M.A., Alhamid, M.F.: A novel comparative deep learning framework for facial age estimation. EURASIP Journal on Image and Video Processing 2016, 1\u201313 (2016)","journal-title":"EURASIP Journal on Image and Video Processing"},{"key":"1797_CR12","doi-asserted-by":"crossref","unstructured":"Xie, H.-X., Lo, L., Shuai, H.-H., Cheng, W.-H.: Au-assisted graph attention convolutional network for micro-expression recognition. In: ACM Int. Conf. Multimedia, pp. 2871\u20132880 (2020)","DOI":"10.1145\/3394171.3414012"},{"key":"1797_CR13","doi-asserted-by":"crossref","unstructured":"Yao, Y., Hsu, C.-F., Lin, J.-H., Xie, H., Lin, T., Huang, Y.-N., Shuai, H.-H., Cheng, W.-H.: The fabrication of reality and fantasy: Scene generation with llm-assisted prompt interpretation. In: European Conference on Computer Vision, pp. 422\u2013438 (2025). Springer","DOI":"10.1007\/978-3-031-72670-5_24"},{"key":"1797_CR14","doi-asserted-by":"crossref","unstructured":"Liu, H.-I., Galindo, M., Xie, H., Wong, L.-K., Shuai, H.-H., Li, Y.-H., Cheng, W.-H.: Lightweight deep learning for resource-constrained environments: A survey. ACM Computing Surveys (2024)","DOI":"10.1145\/3657282"},{"key":"1797_CR15","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"1797_CR16","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., Liang, J.: Decoupled knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"1797_CR17","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: Hints for thin deep nets. In: International Conference on Learning Representations (2015)"},{"key":"1797_CR18","doi-asserted-by":"crossref","unstructured":"Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y.: A comprehensive overhaul of feature distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00201"},{"key":"1797_CR19","doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, S., Zhao, H., Jia, J.: Distilling knowledge via knowledge review. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"1797_CR20","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. In: International Conference on Learning Representations (2020)"},{"key":"1797_CR21","doi-asserted-by":"crossref","unstructured":"Jin, Y., Wang, J., Lin, D.: Multi-level logit distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24276\u201324285 (2023)","DOI":"10.1109\/CVPR52729.2023.02325"},{"key":"1797_CR22","doi-asserted-by":"crossref","unstructured":"Sun, S., Ren, W., Li, J., Wang, R., Cao, X.: Logit standardization in knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15731\u201315740 (2024)","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"1797_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"1797_CR24","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S.I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"1797_CR25","doi-asserted-by":"crossref","unstructured":"Heo, B., Lee, M., Yun, S., Choi, J.Y.: Knowledge transfer via distillation of activation boundaries formed by hidden neurons. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"1797_CR26","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"1797_CR27","doi-asserted-by":"crossref","unstructured":"Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00145"},{"key":"1797_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1797_CR29","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"key":"1797_CR30","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"1797_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"1797_CR32","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. In: British Machine Vision Conference (2016)","DOI":"10.5244\/C.30.87"},{"key":"1797_CR33","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1797_CR34","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1797_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1797_CR36","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: European Conference on Computer Vision, pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1797_CR37","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In: International Conference on Learning Representations (2017)"},{"key":"1797_CR38","doi-asserted-by":"crossref","unstructured":"Guo, Z., Yan, H., Li, H., Lin, X.: Class attention transfer based knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11868\u201311877 (2023)","DOI":"10.1109\/CVPR52729.2023.01142"},{"key":"1797_CR39","unstructured":"Zheng, K., Yang, E.-H.: Knowledge distillation based on transformed teacher matching. In: International Conference on Learning Representations (2024)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01797-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01797-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01797-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:00:03Z","timestamp":1757926803000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01797-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1797"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01797-3","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"assertion":[{"value":"29 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2025","order":3,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"value":"The code is available upon request.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"Stephen Ekaputra Limantoro: Writing, Conceptualization, Methodology, Formal Analysis, and Software. Jhe-Hao Lin: Conceptualization, Validation, and Software. Chih-Yu Wang: Validation and Discussing on the Methods. Yi-Lung Tsai: Validation and Resources. Hong-Han Shuai: Supervision, Validation, and Reviewing. Ching-Chun Huang: Validation, Reviewing, and Discussing on the Methods. Wen-Huang Cheng: Validation, Reviewing, Resources, and Discussing on the Methods. All authors read and approved the manuscript.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Author contribution"}}],"article-number":"264"}}