{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T08:08:39Z","timestamp":1779350919592,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11263-026-02779-2","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:10:24Z","timestamp":1773105024000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-Based Video Incremental Learning"],"prefix":"10.1007","volume":"134","author":[{"given":"Shengqin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoyu","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haokui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuankai","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"2779_CR1","doi-asserted-by":"publisher","unstructured":"Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., & Tuytelaars, T. (2018). Memory aware synapses: Learning what (not) to forget. In: The proceedings of the european conference on computer vision, pp 139\u2013154, https:\/\/doi.org\/10.1007\/978-3-030-01219-9_9.","DOI":"10.1007\/978-3-030-01219-9_9."},{"key":"2779_CR2","doi-asserted-by":"publisher","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., & Schmid, C. (2021). Vivit: A video vision transformer. In: The proceedings of the IEEE\/CVF international conference on computer vision, pp 6836\u20136846,https:\/\/doi.org\/10.1109\/iccv48922.2021.00676.","DOI":"10.1109\/iccv48922.2021.00676."},{"key":"2779_CR3","doi-asserted-by":"crossref","unstructured":"Bang, J., Kim, H., Yoo, Y., Ha, J. W., & Choi, J. (2021). Rainbow memory: Continual learning with a memory of diverse samples. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8218\u20138227.","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"2779_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? a new model and the kinetics dataset. In: The proceedings of the IEEE conference on computer vision and pattern recognition, pp 6299\u20136308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"2779_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Liu, H., Lim, C. H., See, J., Gao, X., Hou, J., & Lin, W. (2025). Csta: Spatial-temporal causal adaptive learning for exemplar-free video class-incremental learning. IEEE Transactions on Circuits and Systems for Video Technology.","DOI":"10.1109\/TCSVT.2025.3579477"},{"key":"2779_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, H., Yang, S., Wang, C., Zhou, J. T., Kot, A. C., & Wen, B. (2024). Stsp: Spatial-temporal subspace projection for video class-incremental learning. In: Proceedings of the european conference on computer vision, Springer, pp 374\u2013391.","DOI":"10.1007\/978-3-031-73390-1_22"},{"key":"2779_CR7","doi-asserted-by":"crossref","unstructured":"Cheraghian, A., Rahman, S., Fang, P., Roy, S. K., Petersson, L., & Harandi, M. (2021). Semantic-aware knowledge distillation for few-shot class-incremental learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2534\u20132543.","DOI":"10.1109\/CVPR46437.2021.00256"},{"key":"2779_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. Preprint arXiv:2010.11929."},{"key":"2779_CR9","doi-asserted-by":"crossref","unstructured":"Douillard, A., Cord, M., Ollion, C., Robert, T., & Valle, E. (2020). Podnet: Pooled outputs distillation for small-tasks incremental learning. In: Proceedings of the european conference on computer vision, Springer, pp 86\u2013102.","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"2779_CR10","doi-asserted-by":"crossref","unstructured":"Goyal, R., Ebrahimi Kahou, S., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. (2017). The\" something something\" video database for learning and evaluating visual common sense. In: The proceedings of the international conference on computer vision, pp 5842\u20135850.","DOI":"10.1109\/ICCV.2017.622"},{"key":"2779_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2779_CR12","doi-asserted-by":"crossref","unstructured":"Hou, S., Pan, X., Loy, C. C., Wang, Z., & Lin, D. (2019). Learning a unified classifier incrementally via rebalancing. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 831\u2013839.","DOI":"10.1109\/CVPR.2019.00092"},{"key":"2779_CR13","doi-asserted-by":"publisher","unstructured":"Kang, M., Park, J., & Han, B. (2022). Class-incremental learning by knowledge distillation with adaptive feature consolidation. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16071\u201316080, https:\/\/doi.org\/10.1109\/cvpr52688.2022.01560.","DOI":"10.1109\/cvpr52688.2022.01560."},{"key":"2779_CR14","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"issue":"13","key":"2779_CR15","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017). Overcoming catastrophic forgetting in neural networks. The Proceedings of the National Academy of Sciences, 114(13), 3521\u20133526.","journal-title":"The Proceedings of the National Academy of Sciences"},{"key":"2779_CR16","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). Hmdb: a large video database for human motion recognition. In: The proceedings of the international conference on computer vision, IEEE, pp 2556\u20132563.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2779_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Shuai, B., & Tighe, J. (2020). Directional temporal modeling for action recognition. In: The proceedings of the european conference on computer vision, Springer, pp 275\u2013291.","DOI":"10.1007\/978-3-030-58539-6_17"},{"issue":"12","key":"2779_CR18","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li, Z., & Hoiem, D. (2017). Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12), 2935\u20132947.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2779_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Su, Y., Liu, A. A., Schiele, B., & Sun, Q. (2020). Mnemonics training: Multi-class incremental learning without forgetting. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12245\u201312254.","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"2779_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022). Video swin transformer. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3202\u20133211.","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2779_CR21","doi-asserted-by":"crossref","unstructured":"Park, J., Kang, M., & Han, B. (2021). Class-incremental learning for action recognition in videos. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 13698\u201313707.","DOI":"10.1109\/ICCV48922.2021.01344"},{"key":"2779_CR22","doi-asserted-by":"crossref","unstructured":"Pei, Y., Qing, Z., Zhang, S., Wang, X., Zhang, Y., Zhao, D., & Qian, X. (2023). Space-time prompting for video class-incremental learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 11932\u201311942.","DOI":"10.1109\/ICCV51070.2023.01096"},{"key":"2779_CR23","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021). Learning transferable visual models from natural language supervision. In: Proceedings of the international conference on machine learning, PmLR, pp 8748\u20138763."},{"key":"2779_CR24","doi-asserted-by":"crossref","unstructured":"Rebuffi, S. A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017). Icarl: Incremental classifier and representation learning. In: The proceedings of the IEEE conference on computer vision and pattern recognition, pp 2001\u20132010.","DOI":"10.1109\/CVPR.2017.587"},{"key":"2779_CR25","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv 2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2779_CR26","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. Preprint arXiv:1212.0402."},{"key":"2779_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In: The proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"2779_CR28","doi-asserted-by":"publisher","unstructured":"Villa, A., Alhamoud, K., Escorcia, V., Caba, F., Alc\u00e1zar, J. L., & Ghanem, B. (2022). vclimb: A novel video class incremental learning benchmark. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19035\u201319044,https:\/\/doi.org\/10.1109\/cvpr52688.2022.01845.","DOI":"10.1109\/cvpr52688.2022.01845."},{"key":"2779_CR29","doi-asserted-by":"crossref","unstructured":"Villa, A., Alc\u00e1zar, J. L., Alfarra, M., Alhamoud, K., Hurtado, J., Heilbron, F. C., Soto, A., & Ghanem, B. (2023). Pivot: Prompting for video continual learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 24214\u201324223.","DOI":"10.1109\/CVPR52729.2023.02319"},{"issue":"11","key":"2779_CR30","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van Gool, L. (2018). Temporal segment networks for action recognition in videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(11), 2740\u20132755.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2779_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., & Wu, G. (2021a). Tdn: Temporal difference networks for efficient action recognition. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1895\u20131904.","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"2779_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., & Smolic, A. (2021b). Action-net: Multipath excitation for action recognition. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13214\u201313223.","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"2779_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C. Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., & Pfister, T. (2022). Learning to prompt for continual learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 139\u2013149.","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"2779_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., & Fu, Y. (2019). Large scale incremental learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 374\u2013382.","DOI":"10.1109\/CVPR.2019.00046"},{"key":"2779_CR35","doi-asserted-by":"crossref","unstructured":"Yan, S., Xie, J., & He, X. (2021). Der: Dynamically expandable representation for class incremental learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3014\u20133023.","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"2779_CR36","doi-asserted-by":"crossref","unstructured":"Yang, J., Dong, X., Liu, L., Zhang, C., Shen, J., & Yu, D. (2022). Recurring the transformer for video action recognition. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14063\u201314073.","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"2779_CR37","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F. E., Li, G., Wang, T., & Feng, J. (2020). Revisiting knowledge distillation via label smoothing regularization. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3903\u20133911.","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"2779_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, J., Ghosh, S., Li, D., Tasci, S., Heck, L., Zhang, H., & Kuo, C. C. J. (2020). Class-incremental learning via deep model consolidation. In: The proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1131\u20131140.","DOI":"10.1109\/WACV45572.2020.9093365"},{"key":"2779_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, B., Xiao, X., Gan, G., Zhang, B., & Xia, S. T. (2020). Maintaining discrimination and fairness in class incremental learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13208\u201313217.","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"2779_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qin, X., Su, S., Fu, Y., Lin, Z., & Li, X. (2021). When video classification meets incremental classes. In: The proceedings of the ACM international conference on multimedia, pp 880\u2013889.","DOI":"10.1145\/3474085.3475265"},{"key":"2779_CR41","doi-asserted-by":"crossref","unstructured":"Zhi, Y., Tong, Z., Wang, L., & Wu, G. (2021). Mgsampler: An explainable sampling strategy for video action recognition. In: The proceedings of the IEEE\/CVF international conference on computer vision, pp 1513\u20131522.","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"2779_CR42","doi-asserted-by":"publisher","unstructured":"Zhou, D. W., Wang, F. Y., Ye, H. J., Ma, L., Pu, S., & Zhan, D. C. (2022). Forward compatible few-shot class-incremental learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9046\u20139056,https:\/\/doi.org\/10.1109\/cvpr52688.2022.00884.","DOI":"10.1109\/cvpr52688.2022.00884."},{"key":"2779_CR43","unstructured":"Zhou, D. W., Wang, Q. W., Ye, H. J., & Zhan, D. C. (2023). A model or 603 exemplars: Towards memory-efficient class-incremental learning. In: International conference on learning representations."},{"key":"2779_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, K., Zhai, W., Cao, Y., Luo, J., & Zha, Z. J. (2022). Self-sustaining representation expansion for non-exemplar class-incremental learning. In: The proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9296\u20139305.","DOI":"10.1109\/CVPR52688.2022.00908"},{"key":"2779_CR45","doi-asserted-by":"crossref","unstructured":"Zou, X., Ma, W., & Zhao, S. (2025). Learning conditional space-time prompt distributions for video class-incremental learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4862\u20134873.","DOI":"10.1109\/CVPR52734.2025.00458"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02779-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02779-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02779-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:31:33Z","timestamp":1779348693000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02779-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2779"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02779-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"17 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"190"}}