{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:45:57Z","timestamp":1793205957325,"version":"4.5.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726453","type":"print"},{"value":"9783031726460","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72646-0_3","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:41:14Z","timestamp":1730104874000},"page":"38-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Efficient Few-Shot Action Recognition via\u00a0Multi-level Post-reasoning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9555-9445","authenticated-orcid":false,"given":"Cong","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0648-8745","authenticated-orcid":false,"given":"Linze","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9015-3128","authenticated-orcid":false,"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4485-4249","authenticated-orcid":false,"given":"Zhenhua","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8110-9205","authenticated-orcid":false,"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Ben-Ari, R., Nacson, M.S., Azulai, O., Barzelay, U., Rotman, D.: TAEN: temporal aware embedding network for few-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 2786\u20132794 (2021). https:\/\/doi.org\/10.1109\/CVPRW53098.2021.00313","DOI":"10.1109\/CVPRW53098.2021.00313"},{"key":"3_CR2","unstructured":"Bishay, M., Zoumpourlis, G., Patras, I.: Tarn: temporal attentive relation network for few-shot and zero-shot action recognition. arXiv preprint arXiv:1907.09021 (2019)"},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Cao, K., Ji, J., Cao, Z., Chang, C.Y., Niebles, J.C.: Few-shot video classification via temporal alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10618\u201310627 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01063","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"3_CR4","doi-asserted-by":"publisher","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.502","DOI":"10.1109\/CVPR.2017.502"},{"key":"3_CR5","unstructured":"Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. In: International Conference on Learning Representations (2019)"},{"key":"3_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/11744047_33","volume-title":"Computer Vision \u2013 ECCV 2006","author":"N Dalal","year":"2006","unstructured":"Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 428\u2013441. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744047_33"},{"key":"3_CR7","unstructured":"Dhillon, G.S., Chaudhari, P., Ravichandran, A., Soatto, S.: A baseline for few-shot image classification. In: International Conference on Learning Representations (2020)"},{"key":"3_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3_CR9","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, vol.\u00a070, pp. 1126\u20131135. PMLR (2017)"},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Fu, M., Zhu, K., Wu, J.: DTL: disentangled transfer learning for visual recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 12082\u201312090 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i11.29096","DOI":"10.1609\/aaai.v38i11.29096"},{"key":"3_CR11","doi-asserted-by":"publisher","unstructured":"Goyal, R., et\u00a0al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5842\u20135850 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.622","DOI":"10.1109\/ICCV.2017.622"},{"key":"3_CR12","unstructured":"Guo, F., Zhu, L., Wang, Y., Qi, H.: Consistency prototype module and motion compensation for few-shot action recognition (clip-cp$$m^2$$c). arXiv preprint arXiv:2312.01083 (2023)"},{"key":"3_CR13","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/978-3-031-19772-7_21","volume-title":"ECCV 2022","author":"Y Huang","year":"2022","unstructured":"Huang, Y., Yang, L., Sato, Y.: Compound prototype matching for few-shot action recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13664, pp. 351\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_21"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3192\u20133199 (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.396","DOI":"10.1109\/ICCV.2013.396"},{"key":"3_CR15","doi-asserted-by":"publisher","unstructured":"Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., Darrell, T.: Few-shot object detection via feature reweighting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8420\u20138429 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00851","DOI":"10.1109\/ICCV.2019.00851"},{"key":"3_CR16","doi-asserted-by":"publisher","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011). https:\/\/doi.org\/10.1109\/ICCV.2011.6126543","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"3_CR17","doi-asserted-by":"publisher","unstructured":"Lan, T., Zhu, Y., Zamir, A.R., Savarese, S.: Action recognition by hierarchical mid-level action elements. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4552\u20134560 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.517","DOI":"10.1109\/ICCV.2015.517"},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"Li, S., et al.: Ta2n: two-stage action alignment network for few-shot action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1404\u20131411 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i2.20029","DOI":"10.1609\/aaai.v36i2.20029"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Li, W., Wang, L., Xu, J., Huo, J., Gao, Y., Luo, J.: Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7260\u20137268 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00743","DOI":"10.1109\/CVPR.2019.00743"},{"issue":"12","key":"3_CR20","doi-asserted-by":"publisher","first-page":"14938","DOI":"10.1109\/TPAMI.2023.3312125","volume":"45","author":"W Li","year":"2023","unstructured":"Li, W., et al.: LibFewShot: a comprehensive library for few-shot learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 14938\u201314955 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3312125","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR21","doi-asserted-by":"publisher","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00718","DOI":"10.1109\/ICCV.2019.00718"},{"key":"3_CR22","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/978-3-031-20044-1_27","volume-title":"ECCV 2022","author":"KD Nguyen","year":"2022","unstructured":"Nguyen, K.D., Tran, Q.H., Nguyen, K., Hua, B.S., Nguyen, R.: Inductive and transductive few-shot video classification via appearance and temporal alignments. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13680, pp. 471\u2013487. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_27"},{"key":"3_CR23","first-page":"26462","volume":"35","author":"J Pan","year":"2022","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: St-adapter: parameter-efficient image-to-video transfer learning. Adv. Neural. Inf. Process. Syst. 35, 26462\u201326477 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR24","unstructured":"Pei, W., Tan, Q., Lu, G., Tian, J.: D$$^2$$st-adapter: Disentangled-and-deformable spatio-temporal adapter for few-shot action recognition. arXiv preprint arXiv:2312.01431 (2023)"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Perrett, T., Masullo, A., Burghardt, T., Mirmehdi, M., Damen, D.: Temporal-relational crosstransformers for few-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 475\u2013484 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00054","DOI":"10.1109\/CVPR46437.2021.00054"},{"issue":"1","key":"3_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s44267-023-00034-7","volume":"2","author":"R Qian","year":"2024","unstructured":"Qian, R., Lin, W., See, J., Li, D.: Controllable augmentations for video representation learning. Visual Intell. 2(1), 1 (2024). https:\/\/doi.org\/10.1007\/s44267-023-00034-7","journal-title":"Visual Intell."},{"key":"3_CR27","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th ACM international conference on Multimedia, pp. 357\u2013360 (2007). https:\/\/doi.org\/10.1145\/1291233.1291311","DOI":"10.1145\/1291233.1291311"},{"key":"3_CR29","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"3_CR30","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3_CR31","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"3_CR32","doi-asserted-by":"publisher","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00131","DOI":"10.1109\/CVPR.2018.00131"},{"key":"3_CR33","first-page":"12991","volume":"35","author":"YL Sung","year":"2022","unstructured":"Sung, Y.L., Cho, J., Bansal, M.: LST: ladder side-tuning for parameter and memory efficient transfer learning. Adv. Neural. Inf. Process. Syst. 35, 12991\u201313005 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR34","doi-asserted-by":"publisher","unstructured":"Thatipelli, A., Narayan, S., Khan, S., Anwer, R.M., Khan, F.S., Ghanem, B.: 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 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01933","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"3_CR35","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et\u00a0al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"issue":"6","key":"3_CR36","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1007\/s11263-023-01917-4","volume":"132","author":"X Wang","year":"2024","unstructured":"Wang, X., et al.: Clip-guided prototype modulating for few-shot action recognition. Int. J. Comput. Vision 132(6), 1899\u20131912 (2024). https:\/\/doi.org\/10.1007\/s11263-023-01917-4","journal-title":"Int. J. Comput. Vision"},{"key":"3_CR37","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: 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 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01727","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"3_CR38","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: Hybrid relation guided set matching for few-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19948\u201319957 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01932","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"3_CR39","unstructured":"Wang, X., et al.: Few-shot action recognition with captioning foundation models. arXiv preprint arXiv:2310.10125 (2023)"},{"issue":"3","key":"3_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","volume":"53","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. (CSUR) 53(3), 1\u201334 (2020). https:\/\/doi.org\/10.1145\/3386252","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"3_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/978-3-540-88688-4_48","volume-title":"Computer Vision \u2013 ECCV 2008","author":"G Willems","year":"2008","unstructured":"Willems, G., Tuytelaars, T., Van Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 650\u2013663. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88688-4_48"},{"key":"3_CR42","doi-asserted-by":"publisher","unstructured":"Wu, C., et al.: SCD-Net: spatiotemporal clues disentanglement network for self-supervised skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 5949\u20135957 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i6.28409","DOI":"10.1609\/aaai.v38i6.28409"},{"key":"3_CR43","doi-asserted-by":"publisher","unstructured":"Wu, J., Zhang, T., Zhang, Z., Wu, F., Zhang, Y.: Motion-modulated temporal fragment alignment network for few-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9151\u20139160 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00894","DOI":"10.1109\/CVPR52688.2022.00894"},{"key":"3_CR44","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-3-031-20062-5_36","volume-title":"ECCV 2022","author":"W Xiang","year":"2022","unstructured":"Xiang, W., Li, C., Wang, B., Wei, X., Hua, X.S., Zhang, L.: Spatiotemporal self-attention modeling with temporal patch shift for action recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13663, pp. 627\u2013644. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_36"},{"key":"3_CR45","unstructured":"Xing, J., Wang, M., Hou, X., Dai, G., Wang, J., Liu, Y.: Multimodal adaptation of clip for few-shot action recognition. arXiv preprint arXiv:2308.01532 (2023)"},{"key":"3_CR46","doi-asserted-by":"publisher","unstructured":"Xing, J., Wang, M., Liu, Y., Mu, B.: Revisiting the spatial and temporal modeling for few-shot action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3001\u20133009 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i3.25403","DOI":"10.1609\/aaai.v37i3.25403"},{"key":"3_CR47","doi-asserted-by":"publisher","unstructured":"Xing, J., et al.: Boosting few-shot action recognition with graph-guided hybrid matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1740\u20131750 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00167","DOI":"10.1109\/ICCV51070.2023.00167"},{"key":"3_CR48","doi-asserted-by":"publisher","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00288","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"3_CR49","unstructured":"Xu, W., Xu, Y., Wang, H., Tu, Z.: Attentional constellation nets for few-shot learning. In: International Conference on Learning Representations (2021)"},{"issue":"1","key":"3_CR50","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s44267-023-00005-y","volume":"1","author":"Y Yang","year":"2023","unstructured":"Yang, Y., Cui, Z., Xu, J., Zhong, C., Zheng, W.S., Wang, R.: Continual learning with Bayesian model based on a fixed pre-trained feature extractor. Visual Intell. 1(1), 5 (2023). https:\/\/doi.org\/10.1007\/s44267-023-00005-y","journal-title":"Visual Intell."},{"key":"3_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-030-58558-7_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Zhang, L., Qi, X., Li, H., Torr, P.H.S., Koniusz, P.: Few-shot action recognition with permutation-invariant attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 525\u2013542. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_31"},{"key":"3_CR52","doi-asserted-by":"publisher","unstructured":"Zhang, S., Zhou, J., He, X.: Learning implicit temporal alignment for few-shot video classification. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, pp. 1309\u20131315 (2021). https:\/\/doi.org\/10.24963\/ijcai.2021\/181","DOI":"10.24963\/ijcai.2021\/181"},{"key":"3_CR53","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-031-19772-7_18","volume-title":"ECCV 2022","author":"S Zheng","year":"2022","unstructured":"Zheng, S., Chen, S., Jin, Q.: Few-shot action recognition with hierarchical matching and contrastive learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13664, pp. 297\u2013313. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_18"},{"key":"3_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1007\/978-3-030-01234-2_46","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Zhu","year":"2018","unstructured":"Zhu, L., Yang, Y.: Compound memory networks for few-shot video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 782\u2013797. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_46"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72646-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:00:45Z","timestamp":1730106045000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72646-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"ISBN":["9783031726453","9783031726460"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72646-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"28 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}