{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:50:48Z","timestamp":1777654248582,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":55,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609079","type":"print"},{"value":"9789819609086","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-981-96-0908-6_26","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:25:30Z","timestamp":1733513130000},"page":"454-471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Telling Stories for\u00a0Common Sense Zero-Shot Action Recognition"],"prefix":"10.1007","author":[{"given":"Shreyank N.","family":"Gowda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Sevilla-Lara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2927\u20132936 (2015)","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"26_CR2","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":"26_CR3","unstructured":"Belghazi, M.I., Baratin, A., Rajeshwar, S., Ozair, S., Bengio, Y., Courville, A., Hjelm, D.: Mutual information neural estimation. In: International conference on machine learning. pp. 531\u2013540. PMLR (2018)"},{"key":"26_CR4","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML. vol.\u00a02, p.\u00a04 (2021)"},{"key":"26_CR5","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":"26_CR6","doi-asserted-by":"crossref","unstructured":"Bucher, M., Herbin, S., Jurie, F.: Generating visual representations for zero-shot classification. In: Proceedings of the IEEE International Conference on Computer Vision Workshops. pp. 2666\u20132673 (2017)","DOI":"10.1109\/ICCVW.2017.308"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: IEEE Conf. Comput. Vis. Pattern Recog. (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"26_CR8","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. arXiv preprint arXiv:1808.01340 (2018)"},{"key":"26_CR9","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":"26_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"26_CR12","unstructured":"Estevam, V., Laroca, R., Menotti, D., Pedrini, H.: Tell me what you see: A zero-shot action recognition method based on natural language descriptions. arXiv preprint arXiv:2112.09976 (2021)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: 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":"26_CR14","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., Mikolov, T.: Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26 (2013)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Gan, C., Lin, M., Yang, Y., De\u00a0Melo, G., Hauptmann, A.G.: Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition. In: Thirtieth AAAI conference on artificial intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10466"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Gan, C., Lin, M., Yang, Y., Zhuang, Y., Hauptmann, A.G.: Exploring semantic inter-class relationships (sir) for zero-shot action recognition. In: Proceedings of the National Conference on Artificial Intelligence (2015)","DOI":"10.1609\/aaai.v29i1.9800"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Gan, C., Yang, T., Gong, B.: Learning attributes equals multi-source domain generalization. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 87\u201397 (2016)","DOI":"10.1109\/CVPR.2016.17"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: I know the relationships: Zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a033, pp. 8303\u20138311 (2019)","DOI":"10.1609\/aaai.v33i01.33018303"},{"issue":"11","key":"26_CR19","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Gowda, S.N.: Synthetic sample selection for generalized zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 58\u201367 (2023)","DOI":"10.1109\/CVPRW59228.2023.00011"},{"key":"26_CR21","unstructured":"Gowda, S.N., Hao, X., Li, G., Sevilla-Lara, L., Gowda, S.N.: Watt for what: Rethinking deep learning\u2019s energy-performance relationship. arXiv preprint arXiv:2310.06522 (2023)"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Keller, F., Sevilla-Lara, L.: Learn2augment: Learning to composite videos for data augmentation in action recognition. In: European Conference on Computer Vision. pp. 242\u2013259. Springer (2022)","DOI":"10.1007\/978-3-031-19821-2_14"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Sevilla-Lara, L.: Smart frame selection for action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a035, pp. 1451\u20131459 (2021)","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Sevilla-Lara, L., Keller, F., Rohrbach, M.: Claster: clustering with reinforcement learning for zero-shot action recognition. In: European Conference on Computer Vision. pp. 187\u2013203. Springer (2022)","DOI":"10.1007\/978-3-031-20044-1_11"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Sevilla-Lara, L., Kim, K., Keller, F., Rohrbach, M.: A new split for evaluating true zero-shot action recognition. arXiv preprint arXiv:2107.13029 (2021)","DOI":"10.1007\/978-3-030-92659-5_12"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Yuan, C.: Colornet: Investigating the importance of color spaces for image classification. In: 14th Asian Conference on Computer Vision, Perth, Australia, December 2\u20136, 2018. pp. 581\u2013596. Springer (2019)","DOI":"10.1007\/978-3-030-20870-7_36"},{"key":"26_CR27","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.neucom.2020.10.080","volume":"430","author":"Z Han","year":"2021","unstructured":"Han, Z., Fu, Z., Li, G., Yang, J.: Inference guided feature generation for generalized zero-shot learning. Neurocomputing 430, 150\u2013158 (2021)","journal-title":"Neurocomputing"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR29","unstructured":"Kim, K., Gowda, S.N., Mac\u00a0Aodha, O., Sevilla-Lara, L.: Capturing temporal information in a single frame: Channel sampling strategies for action recognition. arXiv preprint arXiv:2201.10394 (2022)"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., Fu, Z., Gong, S.: Unsupervised domain adaptation for zero-shot learning. In: Proceedings of the IEEE international conference on computer vision. pp. 2452\u20132460 (2015)","DOI":"10.1109\/ICCV.2015.282"},{"key":"26_CR31","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: 2011 International Conference on Computer Vision. pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Lin, C.C., Lin, K., Wang, L., Liu, Z., Li, L.: Cross-modal representation learning for zero-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19978\u201319988 (2022)","DOI":"10.1109\/CVPR52688.2022.01935"},{"key":"26_CR33","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":"26_CR34","doi-asserted-by":"crossref","unstructured":"Liu, J., Bai, H., Zhang, H., Liu, L.: Beyond normal distribution: More factual feature generation network for generalized zero-shot learning. IEEE MultiMedia (2022)","DOI":"10.1109\/MMUL.2022.3155541"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: 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":"26_CR36","unstructured":"Maaten, L.v.d., Hinton, G.: Visualizing data using t-sne. Journal of machine learning research 9(Nov), 2579\u20132605 (2008)"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Mandal, D., Narayan, S., Dwivedi, S.K., Gupta, V., Ahmed, S., Khan, F.S., Shao, L.: Out-of-distribution detection for generalized zero-shot action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 9985\u20139993 (2019)","DOI":"10.1109\/CVPR.2019.01022"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Mettes, P., Snoek, C.G.: Spatial-aware object embeddings for zero-shot localization and classification of actions. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4443\u20134452 (2017)","DOI":"10.1109\/ICCV.2017.476"},{"key":"26_CR39","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems. pp. 3111\u20133119 (2013)"},{"key":"26_CR40","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"26_CR41","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: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). pp. 372\u2013380. IEEE (2018)","DOI":"10.1109\/WACV.2018.00047"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Ni, B., Peng, H., Chen, M., Zhang, S., Meng, G., Fu, J., Xiang, S., Ling, H.: Expanding language-image pretrained models for general video recognition. In: European Conference on Computer Vision. pp. 1\u201318. Springer (2022)","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Pagliardini, M., Gupta, P., Jaggi, M.: Unsupervised learning of sentence embeddings using compositional n-gram features. In: Proceedings of NAACL-HLT. pp. 528\u2013540 (2018)","DOI":"10.18653\/v1\/N18-1049"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Perrett, T., Masullo, A., Burghardt, T., Mirmehdi, M., Damen, D.: Temporal-relational crosstransformers for few-shot action recognition. arXiv preprint arXiv:2101.06184 (2021)","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"26_CR45","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: European Conference on Computer Vision. pp. 104\u2013120. Springer (2022)","DOI":"10.1007\/978-3-031-19772-7_7"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Qin, J., Liu, L., Shao, L., Shen, F., Ni, B., Chen, J., Wang, Y.: Zero-shot action recognition with error-correcting output codes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2833\u20132842 (2017)","DOI":"10.1109\/CVPR.2017.117"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: Sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (11 2019), https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Regneri, M., Andriluka, M., Amin, S., Pinkal, M., Schiele, B.: Script data for attribute-based recognition of composite activities. In: Eur. Conf. Comput. Vis. (2012)","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"26_CR49","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems. pp. 568\u2013576 (2014)"},{"key":"26_CR50","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":"26_CR51","doi-asserted-by":"crossref","unstructured":"Verma, V.K., Arora, G., Mishra, A., Rai, P.: Generalized zero-shot learning via synthesized examples. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4281\u20134289 (2018)","DOI":"10.1109\/CVPR.2018.00450"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 5542\u20135551 (2018)","DOI":"10.1109\/CVPR.2018.00581"},{"issue":"3","key":"26_CR53","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(3), 309\u2013333 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"26_CR54","doi-asserted-by":"crossref","unstructured":"Xu, X., Hospedales, T.M., Gong, S.: Multi-task zero-shot action recognition with prioritised data augmentation. In: European Conference on Computer Vision. pp. 343\u2013359. Springer (2016)","DOI":"10.1007\/978-3-319-46475-6_22"},{"key":"26_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Long, Y., Guan, Y., Newsam, S., Shao, L.: Towards universal representation for unseen action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 9436\u20139445 (2018)","DOI":"10.1109\/CVPR.2018.00983"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:15:25Z","timestamp":1733516125000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}