{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:19:46Z","timestamp":1791303586976,"version":"4.1.0"},"publisher-location":"Cham","reference-count":70,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729195","type":"print"},{"value":"9783031729201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-72920-1_21","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:02:57Z","timestamp":1727683377000},"page":"369-388","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["C2C: Component-to-Composition Learning for\u00a0Zero-Shot Compositional Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5451-4870","authenticated-orcid":false,"given":"Rongchang","family":"Li","sequence":"first","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\/0000-0002-9015-3128","authenticated-orcid":false,"given":"Tianyang","family":"Xu","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\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1122-0709","authenticated-orcid":false,"given":"Muhammad","family":"Awais","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7576-5791","authenticated-orcid":false,"given":"Sara","family":"Atito","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":[[2024,10,1]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"21_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning, pp. 813\u2013824 (2021)"},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Brattoli, B., Tighe, J., Zhdanov, F., Perona, P., Chalupka, K.: Rethinking zero-shot video classification: end-to-end training for realistic applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4613\u20134623 (2020)","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chao, W.L., Changpinyo, S., Gong, B., Sha, F.: An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In: Proceedings of the European Conference on Computer Vision, pp. 52\u201368 (2016)","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Huang, D.: Elaborative rehearsal for zero-shot action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13638\u201313647 (2021)","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"21_CR8","unstructured":"Chomsky, N.: Aspects of the Theory of Syntax, no.\u00a011. MIT press, Cambridge (2014)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Doshi, K., Yilmaz, Y.: Zero-shot action recognition with transformer-based video semantic embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4858\u20134867 (2023)","DOI":"10.1109\/CVPRW59228.2023.00514"},{"key":"21_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"issue":"1\u20132","key":"21_CR14","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/0010-0277(88)90031-5","volume":"28","author":"JA Fodor","year":"1988","unstructured":"Fodor, J.A., Pylyshyn, Z.W.: Connectionism and cognitive architecture: a critical analysis. Cognition 28(1\u20132), 3\u201371 (1988)","journal-title":"Cognition"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Fu, Y., Hospedales, T.M., Xiang, T., Gong, S.: Attribute learning for understanding unstructured social activity. In: Proceedings of the European Conference on Computer Vision, pp. 530\u2013543 (2012)","DOI":"10.1007\/978-3-642-33765-9_38"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: The \u201csomething something\" video database for learning and evaluating visual common sense. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Gretton, A., Bousquet, O., Smola, A., Sch\u00f6lkopf, B.: Measuring statistical dependence with hilbert-schmidt norms. In: International Conference on Algorithmic Learning Theory, pp. 63\u201377 (2005)","DOI":"10.1007\/11564089_7"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Hao, S., Han, K., Wong, K.Y.K.: Learning attention as disentangler for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15315\u201315324 (2023)","DOI":"10.1109\/CVPR52729.2023.01470"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D cnns retrace the history of 2d cnns and imagenet? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Heckman, J.J.: Sample selection bias as a specification error. Econometrica: J. Econometric Soc. 153\u2013161 (1979)","DOI":"10.2307\/1912352"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Isola, P., Lim, J.J., Adelson, E.H.: Discovering states and transformations in image collections. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1383\u20131391 (2015)","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Ji, J., Krishna, R., Fei-Fei, L., Niebles, J.C.: Action genome: actions as compositions of spatio-temporal scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10236\u201310247 (2020)","DOI":"10.1109\/CVPR42600.2020.01025"},{"issue":"1","key":"21_CR23","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Karthik, S., Mancini, M., Akata, Z.: Kg-sp: knowledge guided simple primitives for open world compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2022)","DOI":"10.1109\/CVPR52688.2022.00912"},{"key":"21_CR25","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Kim, H., Lee, J., Park, S., Sohn, K.: Hierarchical visual primitive experts for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5675\u20135685 (2023)","DOI":"10.1109\/ICCV51070.2023.00522"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Kwon, H., Kim, M., Kwak, S., Cho, M.: Motionsqueeze: neural motion feature learning for video understanding. In: Proceedings of the European Conference on Computer Vision, pp. 345\u2013362 (2020)","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Kwon, H., Kim, M., Kwak, S., Cho, M.: Learning self-similarity in space and time as generalized motion for video action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13065\u201313075 (2021)","DOI":"10.1109\/ICCV48922.2021.01282"},{"key":"21_CR29","unstructured":"Li, K., et al.: Uniformer: unified transformer for efficient spatiotemporal representation learning. arXiv preprint arXiv:2201.04676 (2022)"},{"key":"21_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104244","volume":"114","author":"RC Li","year":"2021","unstructured":"Li, R.C., Wu, X.J., Wu, C., Xu, T.Y., Kittler, J.: Dynamic information enhancement for video classification. Image Vis. Comput. 114, 104244 (2021)","journal-title":"Image Vis. Comput."},{"key":"21_CR31","unstructured":"Li, R., Wu, X.J., Xu, T.: Video is graph: structured graph module for video action recognition. arXiv preprint arXiv:2110.05904 (2021)"},{"issue":"3","key":"21_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3652611","volume":"15","author":"R Li","year":"2024","unstructured":"Li, R., Xu, T., Wu, X.J., Shen, Z., Kittler, J.: Perceiving actions via temporal video frame pairs. ACM Trans. Intell. Syst. Technol. 15(3), 1\u201320 (2024)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, X., Wei, K., Deng, C., Yang, M.: Siamese contrastive embedding network for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9326\u20139335 (2022)","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: temporal excitation and aggregation for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 909\u2013918 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"21_CR35","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., Savarese, S.: Recognizing human actions by attributes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3337\u20133344 (2011)","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Lu, X., Guo, S., Liu, Z., Guo, J.: Decomposed soft prompt guided fusion enhancing for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23560\u201323569 (2023)","DOI":"10.1109\/CVPR52729.2023.02256"},{"key":"21_CR39","doi-asserted-by":"publisher","first-page":"2061","DOI":"10.1109\/TCSVT.2022.3222305","volume":"33","author":"L Ma","year":"2022","unstructured":"Ma, L., Zheng, Y., Zhang, Z., Yao, Y., Fan, X., Ye, Q.: Motion stimulation for compositional action recognition. IEEE Trans. Circuits Syst. Video Technol. 33, 2061\u20132074 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., Akata, Z.: Open world compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5222\u20135230 (2021)","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Mandal, D., et al.: Out-of-distribution detection for generalized zero-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9985\u20139993 (2019)","DOI":"10.1109\/CVPR.2019.01022"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Materzynska, J., Xiao, T., Herzig, R., Xu, H., Wang, X., Darrell, T.: Something-else: compositional action recognition with spatial-temporal interaction networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131059 (2020)","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Misra, I., Gupta, A., Hebert, M.: From red wine to red tomato: composition with context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1792\u20131801 (2017)","DOI":"10.1109\/CVPR.2017.129"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Tombari, F., Akata, Z.: Learning graph embeddings for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 953\u2013962 (2021)","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"21_CR45","unstructured":"Nayak, N.V., Yu, P., Bach, S.: Learning to compose soft prompts for compositional zero-shot learning. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3163\u20133172 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"21_CR47","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":"21_CR48","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Sohn, K.: Dual-path adaptation from image to video transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2203\u20132213 (2023)","DOI":"10.1109\/CVPR52729.2023.00219"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Kuo, W., Angelova, A.: Rethinking video vits: sparse video tubes for joint image and video learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2214\u20132224 (2023)","DOI":"10.1109\/CVPR52729.2023.00220"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Purushwalkam, S., Nickel, M., Gupta, A., Ranzato, M.: Task-driven modular networks for zero-shot compositional learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3593\u20133602 (2019)","DOI":"10.1109\/ICCV.2019.00369"},{"issue":"1","key":"21_CR51","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)","journal-title":"Visual Intell."},{"key":"21_CR52","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yu, L., Liu, W., Hauptmann, A.G.: Rethinking zero-shot action recognition: learning from latent atomic actions. In: Proceedings of the European Conference on Computer Vision, pp. 104\u2013120 (2022)","DOI":"10.1007\/978-3-031-19772-7_7"},{"key":"21_CR53","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":"21_CR54","first-page":"10641","volume":"34","author":"F Ruis","year":"2021","unstructured":"Ruis, F., Burghouts, G., Bucur, D.: Independent prototype propagation for zero-shot compositionality. Adv. Neural. Inf. Process. Syst. 34, 10641\u201310653 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Saini, N., Pham, K., Shrivastava, A.: Disentangling visual embeddings for attributes and objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13658\u201313667 (2022)","DOI":"10.1109\/CVPR52688.2022.01329"},{"key":"21_CR56","doi-asserted-by":"crossref","unstructured":"Sun, P., Wu, B., Li, X., Li, W., Duan, L., Gan, C.: Counterfactual debiasing inference for compositional action recognition. In: Proceedings of the ACM International Conference on Multimedia, pp. 3220\u20133228 (2021)","DOI":"10.1145\/3474085.3475472"},{"key":"21_CR57","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"21_CR58","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"21_CR59","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of the European Conference on Computer Vision, pp. 20\u201336 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"21_CR60","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Learning conditional attributes for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11197\u201311206 (2023)","DOI":"10.1109\/CVPR52729.2023.01077"},{"key":"21_CR61","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision, pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"issue":"1","key":"21_CR62","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s44267-023-00002-1","volume":"1","author":"T Xu","year":"2023","unstructured":"Xu, T., Zhu, X.F., Wu, X.J.: Learning spatio-temporal discriminative model for affine subspace based visual object tracking. Visual Intell. 1(1), 4 (2023)","journal-title":"Visual Intell."},{"key":"21_CR63","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s11263-016-0983-5","volume":"123","author":"X Xu","year":"2017","unstructured":"Xu, X., Hospedales, T., Gong, S.: Transductive zero-shot action recognition by word-vector embedding. Int. J. Comput. Vision 123, 309\u2013333 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"21_CR64","doi-asserted-by":"crossref","unstructured":"Yan, R., Huang, P., Shu, X., Zhang, J., Pan, Y., Tang, J.: Look less think more: rethinking compositional action recognition. In: Proceedings of the ACM International Conference on Multimedia, pp. 3666\u20133675 (2022)","DOI":"10.1145\/3503161.3547862"},{"key":"21_CR65","doi-asserted-by":"publisher","first-page":"10317","DOI":"10.1109\/TPAMI.2023.3261659","volume":"45","author":"R Yan","year":"2023","unstructured":"Yan, R., Xie, L., Shu, X., Zhang, L., Tang, J.: Progressive instance-aware feature learning for compositional action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45, 10317\u2013103330 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR66","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: Aim: adapting image models for efficient video action recognition. arXiv preprint arXiv:2302.03024 (2023)"},{"key":"21_CR67","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"21_CR68","doi-asserted-by":"crossref","unstructured":"Zadrozny, B.: Learning and evaluating classifiers under sample selection bias. In: Proceedings of the International Conference on Machine Learning, p.\u00a0114 (2004)","DOI":"10.1145\/1015330.1015425"},{"key":"21_CR69","doi-asserted-by":"crossref","unstructured":"Zellers, R., Choi, Y.: Zero-shot activity recognition with verb attribute induction. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 946\u2013958 (2017)","DOI":"10.18653\/v1\/D17-1099"},{"issue":"9","key":"21_CR70","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"}],"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\/978-3-031-72920-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:16:34Z","timestamp":1727684194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72920-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729195","9783031729201"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72920-1_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 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"}}]}}