{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:11:35Z","timestamp":1780765895388,"version":"3.54.1"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585570","type":"print"},{"value":"9783030585587","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58558-7_31","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T09:03:08Z","timestamp":1603875788000},"page":"525-542","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":144,"title":["Few-Shot Action Recognition with Permutation-Invariant Attention"],"prefix":"10.1007","author":[{"given":"Hongguang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip H. S.","family":"Torr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Koniusz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"31_CR1","unstructured":"Antoniou, A., Edwards, H., Storkey, A.: How to train your MAML. arXiv preprint (2018)"},{"key":"31_CR2","unstructured":"Bart, E., Ullman, S.: Cross-generalization: Learning novel classes from a single example by feature replacement. In: CVPR (2005)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? a new model and the kinetics dataset. In: CVPR (2018)","DOI":"10.1109\/CVPR.2017.502"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. In: NeurIPS (2014)","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Dwivedi, S.K., Gupta, V., Mitra, R., Ahmed, S., Jain, A.: Protogan: towards few shot learning for action recognition. arXiv preprint (2019)","DOI":"10.1109\/ICCVW.2019.00166"},{"key":"31_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1007\/978-3-030-01216-8_38","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Engin","year":"2018","unstructured":"Engin, M., Wang, L., Zhou, L., Liu, X.: DeepKSPD: learning kernel-matrix-based SPD representation for fine-grained image recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 629\u2013645. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_38"},{"key":"31_CR8","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. In: TPAMI (2006)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.607"},{"key":"31_CR10","unstructured":"Fink, M.: Object classification from a single example utilizing class relevance metrics. In: NeurIPS (2005)"},{"key":"31_CR11","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Gan, C., Gong, B., Liu, K., Su, H., Guibas, L.J.: Geometry guided convolutional neural networks for self-supervised video representation learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00586"},{"key":"31_CR13","unstructured":"Garcia, V., Bruna, J.: Few-shot learning with graph neural networks. In: ICLR (2018)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Bursuc, A., Komodakis, N., P\u00e9rez, P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00815"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Generating classification weights with GNN denoising autoencoders for few-shot learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00011"},{"key":"31_CR16","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint (2018)"},{"key":"31_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/978-3-030-01246-5_40","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Guo","year":"2018","unstructured":"Guo, M., Chou, E., Huang, D.-A., Song, S., Yeung, S., Fei-Fei, L.: Neural graph matching networks for fewshot 3D action recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 673\u2013689. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_40"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.328"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Jian, S., Hu, L., Cao, L., Lu, K.: Representation learning with multiple Lipschitz-constrained alignments on partially-labeled cross-domain data. In: AAAI, pp. 4320\u20134327 (2020)","DOI":"10.1609\/aaai.v34i04.5856"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Jian, S., Hu, L., Cao, L., Lu, K., Gao, H.: Evolutionarily learning multi-aspect interactions and influences from network structure and node content. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 598\u2013605 (2019)","DOI":"10.1609\/aaai.v33i01.3301598"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, T., Kim, S., Yoo, C.D.: Edge-labeling graph neural network for few-shot learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00010"},{"key":"31_CR22","unstructured":"Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop (2015)"},{"key":"31_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-319-46493-0_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Koniusz","year":"2016","unstructured":"Koniusz, P., Cherian, A., Porikli, F.: Tensor representations via kernel linearization for action recognition from 3D skeletons. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 37\u201353. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_3"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Koniusz, P., Tas, Y., Porikli, F.: Domain adaptation by mixture of alignments of second-or higher-order scatter tensors. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.755"},{"key":"31_CR25","unstructured":"Koniusz, P., Wang, L., Cherian, A.: Tensor representations for action recognition. TPAMI (2020)"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Koniusz, P., Yan, F., Gosselin, P.H., Mikolajczyk, K.: Higher-order occurrence pooling for bags-of-words: Visual concept detection. TPAMI (2017)","DOI":"10.1109\/TPAMI.2016.2545667"},{"key":"31_CR27","unstructured":"Koniusz, P., Zhang, H.: Power normalizations in fine-grained image, few-shot image and graph classification. TPAMI (2020)"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Koniusz, P., Zhang, H., Porikli, F.: A deeper look at power normalizations. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00605"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Lai, Z., Lu, E., Xie, W.: Mast: a memory-augmented self-supervised tracker. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"31_CR31","unstructured":"Lake, B.M., Salakhutdinov, R., Gross, J., Tenenbaum, J.B.: One shot learning of simple visual concepts. CogSci (2011)"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01091"},{"key":"31_CR33","doi-asserted-by":"publisher","first-page":"9596","DOI":"10.1073\/pnas.092277599","volume":"99","author":"FF Li","year":"2002","unstructured":"Li, F.F., VanRullen, R., Koch, C., Perona, P.: Rapid natural scene categorization in the near absence of attention. Proc. Natl. Acad. Sci. 99, 9596\u20139601 (2002)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"31_CR34","unstructured":"Miller, E.G., Matsakis, N.E., Viola, P.A.: Learning from one example through shared densities on transforms. In: CVPR (2000)"},{"key":"31_CR35","doi-asserted-by":"crossref","unstructured":"Mishra, A., Verma, V.K., Reddy, M.S.K., Arulkumar, S., Rai, P., Mittal, A.: A generative approach to zero-shot and few-shot action recognition. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00047"},{"key":"31_CR36","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. TPAMI (2019)"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Romero, A., Ter\u00e1n, M.Y., Gouiff\u00e8s, M., Lacassagne, L.: Enhanced local binary covariance matrices (ELBCM) for texture analysis and object tracking. MIRAGE (2013)","DOI":"10.1145\/2466715.2466733"},{"key":"31_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O.: ImageNet largescale visual recognition challenge. IJCV 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"IJCV"},{"key":"31_CR39","unstructured":"Rusu, A.A., Rao, D., Sygnowski, J., Vinyals, O., Pascanu, R., Osindero, S., Hadsell, R.: Meta-learning with latent embedding optimization. In: ICLR (2019)"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Lynch, C., Chebotar, Y., Hsu, J., Jang, E., Schaal, S., Levine, S.: Time-contrastive networks: self-supervised learning from pixels. In: ICRA (2017)","DOI":"10.1109\/CVPRW.2017.69"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., Nock, R., Harandi, M.: Deep subspace networks for few-shot learning. In: NeurIPS Workshops (2019)","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"31_CR42","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., Nock, R., Harandi, M.: Adaptive subspaces for few-shot learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., Nock, R., Harandi, M.: On modulating the gradient formeta-learning. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58598-3_33"},{"key":"31_CR44","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NeurIPS (2017)"},{"key":"31_CR45","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint (2012)"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Su, J.C., Maji, S., Hariharan, B.: Boosting supervision with self-supervision for few-shot learning. arXiv preprint (2019)","DOI":"10.1007\/978-3-030-58571-6_38"},{"key":"31_CR47","doi-asserted-by":"crossref","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"31_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/11744047_45","volume-title":"Computer Vision \u2013 ECCV 2006","author":"O Tuzel","year":"2006","unstructured":"Tuzel, O., Porikli, F., Meer, P.: Region covariance: a fast descriptor for detection and classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 589\u2013600. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744047_45"},{"key":"31_CR49","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NeurIPS (2016)"},{"key":"31_CR50","doi-asserted-by":"publisher","unstructured":"Wang, L., Zhang, J., Zhou, L., Tang, C., Li, W.: Beyond covariance: Feature representation with nonlinear kernel matrices. In: ICCV, pp. 4570\u20134578 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.519","DOI":"10.1109\/ICCV.2015.519"},{"key":"31_CR51","doi-asserted-by":"crossref","unstructured":"Wertheimer, D., Hariharan, B.: Few-shot learning with localization in realistic settings. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00672"},{"key":"31_CR52","doi-asserted-by":"crossref","unstructured":"Xu, B., Ye, H., Zheng, Y., Wang, H., Luwang, T., Jiang, Y.G.: Dense dilated network for few shot action recognition. In: ICMR (2018)","DOI":"10.1145\/3206025.3206028"},{"key":"31_CR53","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"31_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koniusz, P.: Power normalizing second-order similarity network for few-shot learning. In: WACV (2019)","DOI":"10.1109\/WACV.2019.00131"},{"key":"31_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, J., Koniusz, P.: Few-shot learning via saliency-guided hallucination of samples. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00288"},{"key":"31_CR56","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NeurIPS (2014)"},{"key":"31_CR57","unstructured":"Zhu, F., Zhang, L., Fu, Y., Guo, G., Xie, W.: Self-supervised video object segmentation. arXiv preprint (2020)"},{"key":"31_CR58","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"},{"key":"31_CR59","unstructured":"Zintgraf, L., Shiarli, K., Kurin, V., Hofmann, K., Whiteson, S.: Fast context adaptation via meta-learning. In: ICML (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58558-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:56:11Z","timestamp":1730105771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58558-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585570","9783030585587"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58558-7_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 October 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}