{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T17:03:23Z","timestamp":1784567003576,"version":"3.55.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"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":[[2026,6]]},"DOI":"10.1007\/s11263-026-02895-z","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:14:19Z","timestamp":1779912859000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7280-249X","authenticated-orcid":false,"given":"Jiazheng","family":"Xing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hangjie","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengmeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Dan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hangwei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"2895_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., & Anadkat, S. (2023). Gpt-4 technical report, arXiv:2303.08774."},{"key":"2895_CR2","unstructured":"Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., Ge, W., Guo, Z., Huang, Q., Huang, J., Huang, F., Hui, B., Jiang, S., Li, Z., Li, M., Li, M., Li, K., Lin, Z., Lin, J., Liu, X., Liu, J., Liu, C., Liu, Y., Liu, D., Liu, S., Lu, D., Luo, R., Lv, C., Men, R., Meng, L., Ren, X., Ren, X., Song, S., Sun, Y., Tang, J., Tu, J., Wan, J., Wang, P., Wang, P., Wang, Q., Wang, Y., Xie, T., Xu, Y., Xu, H., Xu, J., Yang, Z., Yang, M., Yang, J., Yang, A., Yu, B., Zhang, F., Zhang, H., Zhang, X., Zheng, B., Zhong, H., Zhou, J., Zhou, F., Zhou, J., Zhu, Y.,& Zhu, K. (2025). Qwen3-VL Technical Report, https:\/\/arxiv.org\/abs\/2511.21631."},{"key":"2895_CR3","doi-asserted-by":"publisher","first-page":"6833","DOI":"10.52202\/079017-0219","volume":"37","author":"Z Bai","year":"2024","unstructured":"Bai, Z., He, T., Mei, H., Wang, P., Gao, Z., Chen, J., Zhang, Z., & Shou, M. Z. (2024). One token to seg them all: Language instructed reasoning segmentation in videos. Advances in Neural Information Processing Systems, 37, 6833\u20136859.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2895_CR4","doi-asserted-by":"crossref","unstructured":"Cao, K., Ji, J., Cao, Z., Chang, C.-Y., & Niebles, J.C. (2020).Few-shot video classification via temporal alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10618\u201310627.","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"2895_CR5","doi-asserted-by":"crossref","unstructured":"Cao, C., Zhang, Y., Yu, Y., Lv, Q., Min, L., & Zhang, Y. (2024). Task-adapter: Task-specific adaptation of image models for few-shot action recognition. arXiv:2408.00249 .","DOI":"10.2139\/ssrn.5652981"},{"key":"2895_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? a new model and the kinetics dataset. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6299\u20136308).","DOI":"10.1109\/CVPR.2017.502"},{"key":"2895_CR7","unstructured":"Chiang, W.-L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J.E., and others (2023). Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See lmsys. org (accessed 14 April 2023) 2(3), 6."},{"key":"2895_CR8","unstructured":"Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. International Conference on Machine Learning (pp. 1126\u20131135) PMLR."},{"issue":"3","key":"2895_CR9","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TNNLS.2020.3041018","volume":"33","author":"Z Gao","year":"2020","unstructured":"Gao, Z., Guo, L., Ren, T., Liu, A.-A., Cheng, Z.-Y., & Chen, S. (2020). Pairwise two-stream convnets for cross-domain action recognition with small data. IEEE Transactions on Neural Networks and Learning Systems, 33(3), 1147\u20131161.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2895_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. (2017). The\" something something\" video database for learning and evaluating visual common sense. Proceedings of the IEEE International Conference on Computer Vision (pp. 5842\u20135850).","DOI":"10.1109\/ICCV.2017.622"},{"issue":"9","key":"2895_CR11","doi-asserted-by":"publisher","first-page":"3977","DOI":"10.1007\/s11263-024-02017-7","volume":"132","author":"Y Huang","year":"2024","unstructured":"Huang, Y., Yang, L., Chen, G., Zhang, H., Lu, F., & Sato, Y. (2024). Matching compound prototypes for few-shot action recognition. International Journal of Computer Vision, 132(9), 3977\u20134002.","journal-title":"International Journal of Computer Vision"},{"key":"2895_CR12","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. 2011 International Conference on Computer Vision (pp. 2556\u20132563). IEEE.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2895_CR13","doi-asserted-by":"crossref","unstructured":"Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., & Jia, J. (2024). Lisa: Reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9579\u20139589.","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"2895_CR14","doi-asserted-by":"crossref","unstructured":"Lee, S., Moon, W., Seong, H. S., & Heo, J.-P. (2025). Temporal alignment-free video matching for few-shot action recognition. Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 5412\u20135421)","DOI":"10.1109\/CVPR52734.2025.00509"},{"key":"2895_CR15","unstructured":"Li, K., He, Y., Wang, Y., Li, Y., Wang, W., Luo, P., Wang, Y., Wang, L., & Qiao, Y. (2023). Videochat: Chat-centric video understanding.arXiv:2305.06355."},{"key":"2895_CR16","unstructured":"Li, J., Li, D., Xiong, C., & Hoi, S. (2022). Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR"},{"key":"2895_CR17","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., & Yuan, L. (2023). Video-llava: Learning united visual representation by alignment before projection, arXiv:2311.10122.","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"2895_CR18","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., & Lee, Y.J. (2024). Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306.","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"2895_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2024). Visual instruction tuning. Advances in neural information processing systems (p. 36).","DOI":"10.52202\/075280-1516"},{"key":"2895_CR20","unstructured":"Nichol, A., & Schulman, J. (2018). Reptile: a scalable metalearning algorithm. arXiv:1803.02999 2(3), 4."},{"key":"2895_CR21","unstructured":"Peng, Z., Wang, W., Dong, L., Hao, Y., Huang, S., Ma, S., & Wei, F. (2023). Kosmos-2: Grounding multimodal large language models to the world arXiv:2306.14824 ."},{"key":"2895_CR22","doi-asserted-by":"crossref","unstructured":"Perrett, T., Masullo, A., Burghardt, T., Mirmehdi, M., & Damen, D. (2021). Temporal-relational crosstransformers for few-shot action recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 475\u2013484).","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"2895_CR23","doi-asserted-by":"crossref","unstructured":"Qu, H., Yan, R., Shu, X., Gao, H., Huang, P., & Xie, G.-S. (2024). Mvp-shot: Multi-velocity progressive-alignment framework for few-shot action recognition, arXiv:2405.02077 .","DOI":"10.1109\/TMM.2025.3586118"},{"key":"2895_CR24","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., & Clark, J. (2021). Learning transferable visual models from natural language supervision. International Conference on Machine Learning (pp. 8748\u20138763) PMLR."},{"key":"2895_CR25","unstructured":"Snell, J., Swersky, K., & Zemel, R. (2017). Prototypical networks for few-shot learning. Advances in neural information processing systems (p. 30)."},{"key":"2895_CR26","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402."},{"key":"2895_CR27","doi-asserted-by":"crossref","unstructured":"Thatipelli, A., Narayan, S., Khan, S., Anwer, R.M., Khan, F.S., & Ghanem, B. (2022). Spatio-temporal relation modeling for few-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19958\u201319967.","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"2895_CR28","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., & Azhar, F. (2023). Llama: Open and efficient foundation language models, arXiv:2302.13971 ."},{"key":"2895_CR29","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., & Wierstra, D. (2016). Matching networks for one shot learning. Advances in neural information processing systems, 29."},{"key":"2895_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., & Ke, L. (2024). Llm-seg: Bridging image segmentation and large language model reasoning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 1765\u20131774).","DOI":"10.1109\/CVPRW63382.2024.00183"},{"key":"2895_CR31","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W., and others. (2024). Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv:2409.12191."},{"key":"2895_CR32","unstructured":"Wang, M., Xing, J., Mei, J., Liu, Y., & Jiang, Y. (2023). Actionclip: Adapting language-image pretrained models for video action recognition. IEEE Transactions on Neural Networks and Learning Systems."},{"key":"2895_CR33","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Gool, L.V. (2016). Temporal segment networks: Towards good practices for deep action recognition. In: European Conference on Computer Vision, pp. 20\u201336. Springer.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"2895_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, S., Cen, J., Gao, C., Zhang, Y., Zhao, D., & Sang, N. (2023). Clip-guided prototype modulating for few-shot action recognition. arXiv:2303.02982.","DOI":"10.1007\/s11263-023-01917-4"},{"key":"2895_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, S., Qing, Z., Gao, C., Zhang, Y., Zhao, D., & Sang, N. (2023). Molo: Motion-augmented long-short contrastive learning for few-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18011\u201318021.","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"2895_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, S., Qing, Z., Tang, M., Zuo, Z., Gao, C., Jin, R., & Sang, N. (2022). Hybrid relation guided set matching for few-shot action recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 19948\u201319957).","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"2895_CR37","unstructured":"Wang, X., Zhang, S., Yuan, H., Zhang, Y., Gao, C., Zhao, D., & Sang, N. (2023). Few-shot action recognition with captioning foundation models. arXiv:2310.10125."},{"issue":"3","key":"2895_CR38","first-page":"3347","volume":"45","author":"M Wang","year":"2022","unstructured":"Wang, M., Xing, J., Su, J., Chen, J., & Liu, Y. (2022). Learning spatiotemporal and motion features in a unified 2d network for action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 3347\u20133362.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2895_CR39","doi-asserted-by":"crossref","unstructured":"Wu, C., Wu, X.-J., Li, L., Xu, T., Feng, Z., & Kittler, J. (2024). Efficient few-shot action recognition via multi-level post-reasoning. In: European Conference on Computer Vision, pp. 38\u201356. Springer.","DOI":"10.1007\/978-3-031-72646-0_3"},{"key":"2895_CR40","doi-asserted-by":"crossref","unstructured":"Xing, J., Wang, M., Hou, X., Dai, G., Wang, J., & Liu, Y. (2023). Multimodal adaptation of clip for few-shot action recognition.arXiv:2308.01532.","DOI":"10.2139\/ssrn.5055942"},{"key":"2895_CR41","doi-asserted-by":"crossref","unstructured":"Xing, J., Wang, M., Mu, B., & Liu, Y. (2023). Revisiting the spatial and temporal modeling for few-shot action recognition, arXiv:2301.07944 .","DOI":"10.1609\/aaai.v37i3.25403"},{"key":"2895_CR42","doi-asserted-by":"crossref","unstructured":"Xing, J., Wang, M., Ruan, Y., Chen, B., Guo, Y., Mu, B., Dai, G., Wang, J., & Liu, Y. (2023). Boosting few-shot action recognition with graph-guided hybrid matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1740\u20131750.","DOI":"10.1109\/ICCV51070.2023.00167"},{"key":"2895_CR43","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., Zheng, C., Liu, D., Zhou, F., Huang, F., Hu, F., Ge, H., Wei, H., Lin, H., Tang, J., Yang, J., Tu, J., Zhang, J., Yang, J., Yang, J., Zhou, J., Zhou, J., Lin, J., Dang, K., Bao, K., Yang, K., Yu, L., Deng, L., Li, M., Xue, M., Li, M., Zhang, P., Wang, P., Zhu, Q., Men, R., Gao, R., Liu, S., Luo, S., Li, T., Tang, T., Yin, W., Ren, X., Wang, X., Zhang, X., Ren, X., Fan, Y., Su, Y., Zhang, Y., Zhang, Y., Wan, Y., Liu, Y., Wang, Z., Cui, Z., Zhang, Z., Zhou, Z., & Qiu, Z. (2025). Qwen3 Technical Report. https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"2895_CR44","unstructured":"Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., Wei, H., and others (2024). Qwen2. 5 technical report. arXiv:2412.15115."},{"key":"2895_CR45","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., & Li, M. (2023). Aim: Adapting image models for efficient video action recognition,arXiv:2302.03024."},{"key":"2895_CR46","unstructured":"Zang, Y., Li, W., Han, J., Zhou, K., & Loy, C. C. (2023). Contextual object detection with multimodal large language models, arXiv:2305.18279 ."},{"key":"2895_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., & Bing, L. (2023). Video-llama: An instruction-tuned audio-visual language model for video understanding arXiv:2306.02858","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"2895_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, L., Qi, X., Li, H., Torr, P.H., & Koniusz, P. (2020). Few-shot action recognition with permutation-invariant attention. In: European Conference on Computer Vision, pp. 525\u2013542. Springer.","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"2895_CR49","doi-asserted-by":"crossref","unstructured":"Zheng, S., Chen, S., & Jin, Q. (2022). Few-shot action recognition with hierarchical matching and contrastive learning. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IV, pp. 297\u2013313. Springer.","DOI":"10.1007\/978-3-031-19772-7_18"},{"key":"2895_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, L., & Yang, Y. (2018). Compound memory networks for few-shot video classification. Proceedings of the European Conference on Computer Vision (ECCV) (pp. 751\u2013766).","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"2895_CR51","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., & Elhoseiny, M. (2023). Minigpt-4: Enhancing vision-language understanding with advanced large language models, arXiv preprint arXiv:2304.10592."},{"key":"2895_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, L., Guo, S., & Wu, G. (2021). A closer look at few-shot video classification: a new baseline and benchmark, arXiv preprint arXiv:2110.12358.","DOI":"10.5244\/C.35.50"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02895-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02895-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02895-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:17:00Z","timestamp":1784564220000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02895-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2895"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02895-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]},"assertion":[{"value":"22 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"291"}}