{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:53:50Z","timestamp":1785336830098,"version":"3.55.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,1,10]],"date-time":"2017-01-10T00:00:00Z","timestamp":1484006400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1007\/s11263-016-0983-5","type":"journal-article","created":{"date-parts":[[2017,1,10]],"date-time":"2017-01-10T08:01:14Z","timestamp":1484035274000},"page":"309-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":116,"title":["Transductive Zero-Shot Action Recognition by Word-Vector Embedding"],"prefix":"10.1007","volume":"123","author":[{"given":"Xun","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy","family":"Hospedales","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaogang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,1,10]]},"reference":[{"issue":"3","key":"983_CR1","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1145\/1922649.1922653","volume":"43","author":"J Aggarwal","year":"2011","unstructured":"Aggarwal, J., & Ryoo, M. (2011). Human activity analysis: A review. ACM Computer Survey, 43(3), 16.","journal-title":"ACM Computer Survey"},{"key":"983_CR2","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., & Schiele, B. (2015). Evaluation of output embeddings for fine-grained image classification. In CVPR (pp. 2927\u20132936).","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"983_CR3","first-page":"2399","volume":"7","author":"M Belkin","year":"2006","unstructured":"Belkin, M., Niyogi, P., & Sindhwani, V. (2006). Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. The Journal of Machine Learning Research, 7, 2399\u20132434.","journal-title":"The Journal of Machine Learning Research"},{"key":"983_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Cui, Y., Ye, G., Liu, D., & Chang, SF. (2014). Event-driven semantic concept discovery by exploiting weakly tagged internet images. In ICMR (p. 1).","DOI":"10.1145\/2578726.2578729"},{"key":"983_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., & Li, F. (2009). Imagenet: A large-scale hierarchical image database. In CVPR (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"983_CR6","unstructured":"Dinu, G., Lazaridou, A., & Baroni, M. (2015). Improving zero-shot learning by mitigating the hubness problem. In ICLR, Workshop Track."},{"key":"983_CR7","unstructured":"Frome, A., Corrado, G. S., & Shlens, J. (2013). Devise: A deep visual-semantic embedding model. In NIPS (pp. 2121\u20132129)."},{"key":"983_CR8","doi-asserted-by":"crossref","unstructured":"Fu, Y., Hospedales, T. M., Xiang, T., & Gong, S. (2012). Attribute learning for understanding unstructured social activity. In ECCV (pp. 530\u2013543).","DOI":"10.1007\/978-3-642-33765-9_38"},{"key":"983_CR9","doi-asserted-by":"crossref","unstructured":"Fu, Y., Hospedales, T. M., Xiang, T., Fu, Z., & Gong, S. (2014a). Transductive multi-view embedding for zero-shot recognition and annotation. In ECCV (pp. 584\u2013599).","DOI":"10.1007\/978-3-319-10605-2_38"},{"issue":"2","key":"983_CR10","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TPAMI.2013.128","volume":"36","author":"Y Fu","year":"2014","unstructured":"Fu, Y., Hospedales, T. M., Xiang, T., & Gong, S. (2014b). Learning multimodal latent attributes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(2), 303\u2013316.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"983_CR11","doi-asserted-by":"crossref","unstructured":"Fu, Y., Yang, Y., & Gong, S. (2014c). Transductive multi-label zero-shot learning. In BMVC (pp. 1\u20135).","DOI":"10.5244\/C.28.7"},{"issue":"11","key":"983_CR12","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1109\/TPAMI.2015.2408354","volume":"37","author":"Y Fu","year":"2015","unstructured":"Fu, Y., Hospedales, T. M., Xiang, T., & Gong, S. (2015a). Transductive multi-view zero-shot learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(11), 2332\u20132345.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"983_CR13","doi-asserted-by":"crossref","unstructured":"Fu, Z., Xiang, T., Kodirov, E., & Gong, S. (2015b). Zero-shot object recognition by semantic manifold distance. In CVPR (pp. 2635\u20132644).","DOI":"10.1109\/CVPR.2015.7298879"},{"key":"983_CR14","doi-asserted-by":"crossref","unstructured":"Gan, C., Lin, M., Yang, Y., Zhuang, Y., & GHauptmann, A. (2015). Exploring semantic inter-class relationships (sir) for zero-shot action recognition. In AAAI (pp. 3769\u20133775).","DOI":"10.1609\/aaai.v29i1.9800"},{"issue":"12","key":"983_CR15","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick, L., Blank, M., Shechtman, E., Irani, M., & Basri, R. (2007). Actions as space-time shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(12), 2247\u20132253.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"983_CR16","doi-asserted-by":"crossref","unstructured":"Habibian, A., Mensink, T., & Snoek, C. G. (2014a). Composite concept discovery for zero-shot video event detection. In ICMR (p. 17).","DOI":"10.1145\/2578726.2578746"},{"key":"983_CR17","doi-asserted-by":"crossref","unstructured":"Habibian, A., Mensink, T., & Snoek, C. G. M. (2014b). VideoStory: A new multimedia embedding for few-example recognition and translation of events. In ACM Multimedia (pp. 17\u201326).","DOI":"10.1145\/2647868.2654913"},{"key":"983_CR18","unstructured":"Jain, M., & Snoek, C. G. M. (2015). What do 15,000 object categories tell us about classifying and localizing actions? In CVPR (pp. 46\u201355)."},{"key":"983_CR19","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J. C., Mensink, T., & Snoek, C. G. M. (2015). Objects2action: Classifying and localizing actions without any video example. In ICCV (pp. 4588\u20134596).","DOI":"10.1109\/ICCV.2015.521"},{"key":"983_CR20","unstructured":"Jiang, Y., Wu, Z., Wang, J., Xue, X., & Chang, S. (2015). Exploiting feature and class relationships in video categorization with regularized deep neural networks. arXiv preprint arXiv:1502.07209 ."},{"key":"983_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, Y. G., Ye, G., Chang, S. F., Ellis, D. P. W., & Loui, A. C. (2011). Consumer video understanding: A benchmark database and an evaluation of human and machine performance. In ICMR (p. 29).","DOI":"10.1145\/1991996.1992025"},{"key":"983_CR22","unstructured":"Jiang, Y. G., Liu, J., Zamir A. R., Laptev, I., Piccardi, M., Shah, M., & Sukthankar, R. (2013). THUMOS challenge: Action recognition with a large number of classes."},{"key":"983_CR23","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marsza\u0142ek, M., & Schmid, C. (2008). A spatio-temporal descriptor based on 3d-gradients. In BMVC (pp 1\u201310).","DOI":"10.5244\/C.22.99"},{"key":"983_CR24","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., Fu, Z., & Gong, S. (2015). Unsupervised domain adaptation for zero-shot learning. In ICCV (pp 2452\u20132460).","DOI":"10.1109\/ICCV.2015.282"},{"key":"983_CR25","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). Hmdb: A large video database for human motion recognition. In ICCV (pp 2556\u20132563).","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"983_CR26","doi-asserted-by":"crossref","unstructured":"Lampert, CH., Nickisch, H., & Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In CVPR (pp 951\u2013958).","DOI":"10.1109\/CVPR.2009.5206594"},{"issue":"3","key":"983_CR27","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1109\/TPAMI.2013.140","volume":"36","author":"CH Lampert","year":"2014","unstructured":"Lampert, C. H., Nickisch, H., & Harmeling, S. (2014). Attribute-based classification for zero-shot visual object categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3), 453\u2013465.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2\u20133","key":"983_CR28","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I. (2005). On space-time interest points. International Journal of Computer Vision, 64(2\u20133), 107\u2013123.","journal-title":"International Journal of Computer Vision"},{"key":"983_CR29","unstructured":"Larochelle, H., Erhan, D., & Bengio, Y. (2008). Zero-data learning of new tasks. In AAAI (pp 646\u2013651)."},{"key":"983_CR30","doi-asserted-by":"crossref","unstructured":"Lazaridou, A., Bruni, E., & Baroni, M. (2014). Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world. In ACL (pp 1403\u20131414).","DOI":"10.3115\/v1\/P14-1132"},{"key":"983_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., & Savarese, S. (2011). Recognizing human actions by attributes. In CVPR (pp 3337\u20133344).","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"983_CR32","first-page":"2579","volume":"9","author":"LVD Maaten","year":"2008","unstructured":"Maaten, L. V. D., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"983_CR33","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., & Schmid, C. (2009). Actions in context. In CVPR (pp 2929\u20132936).","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"983_CR34","doi-asserted-by":"crossref","unstructured":"Mensink, T., Gavves, E., & Snoek, C. G. (2014). Costa: Co-occurrence statistics for zero-shot classification. In CVPR (pp. 2441\u20132448).","DOI":"10.1109\/CVPR.2014.313"},{"key":"983_CR35","unstructured":"Mikolov, T., Sutskever, I., & Chen, K. (2013). Distributed representations of words and phrases and their compositionality. In NIPS (pp. 3111\u20133119)."},{"key":"983_CR36","doi-asserted-by":"crossref","unstructured":"Milajevs, D., Kartsaklis, D., Sadrzadeh, M., & Purver, M. (2014). Evaluating neural word representations in tensor-based compositional settings. In EMNLP (pp. 708\u2013719).","DOI":"10.3115\/v1\/D14-1079"},{"key":"983_CR37","unstructured":"Mitchell, J., & Lapata, M. (2008). Vector-based models of semantic composition. In ACL (pp. 236\u2013244)."},{"key":"983_CR38","doi-asserted-by":"crossref","unstructured":"Niebles, CWFFL Juan Carlos Chen. (2010). Modeling temporal structure of decomposable motion segments for activity classification. In ECCV (pp 392\u2013405).","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"983_CR39","unstructured":"Norouzi, M., Mikolov, T., Bengio, S., Singer, Y., Shlens, J., Frome, A., Corrado, G. S., & Dean, J. (2014). Zero-shot learning by convex combination of semantic embeddings. In ICLR."},{"key":"983_CR40","unstructured":"Over, P., Fiscus, J., Sanders, G., Joy, D., Michel, M., Smeaton-Alan, A. F., & Qu\u00e9not-Georges, G. (2014). Trecvid 2013\u2014An overview of the goals, tasks, data, evaluation mechanisms, and metrics."},{"key":"983_CR41","unstructured":"Palatucci, M., Hinton, G., Pomerleau, D., & Mitchell, T. M. (2009). Zero-shot learning with semantic output codes. In NIPS (pp. 1410\u20131418)."},{"issue":"10","key":"983_CR42","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345\u20131359.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"983_CR43","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., & Mensink, T. (2010). Improving the fisher kernel for large-scale image classification. In ECCV (pp. 143\u2013156).","DOI":"10.1007\/978-3-642-15561-1_11"},{"issue":"6","key":"983_CR44","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R. (2010). A survey on vision-based human action recognition. Image and Vision Computing, 28(6), 976\u2013990.","journal-title":"Image and Vision Computing"},{"key":"983_CR45","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Stark, M., Szarvas, G., Gurevych, I., & Schiele, B. (2010). What helps where- and why? Semantic relatedness for knowledge transfer. In CVPR (pp. 910\u2013917).","DOI":"10.1109\/CVPR.2010.5540121"},{"key":"983_CR46","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Stark, M., & Schiele, B. (2011). Evaluating knowledge transfer and zero-shot learning in a large-scale setting. In CVPR (pp. 1641\u20131648).","DOI":"10.1109\/CVPR.2011.5995627"},{"key":"983_CR47","unstructured":"Rohrbach, M., Ebert, S., & Schiele, B. (2013). Transfer learning in a transductive setting. In NIPS (pp. 46\u201354)."},{"issue":"3","key":"983_CR48","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1007\/s11263-015-0851-8","volume":"119","author":"M Rohrbach","year":"2016","unstructured":"Rohrbach, M., Rohrbach, A., Regneri, M., Amin, S., Andriluka, M., Pinkal, M., et al. (2016). Recognizing fine-grained and composite activities using hand-centric features and script data. IJCV, 119(3), 346\u2013373.","journal-title":"IJCV"},{"key":"983_CR49","unstructured":"Romera-Paredes, B., & Torr, P. H. S. (2015). An embarrassingly simple approach to zero-shot learning. In ICML (pp. 2152\u20132161)."},{"key":"983_CR50","volume-title":"Learning with kernels: Support vector machines, regularization, optimization, and beyond","author":"B Scholkopf","year":"2002","unstructured":"Scholkopf, B., & Smola, A. J. (2002). Learning with kernels: Support vector machines, regularization, optimization, and beyond. Cambridge: MIT Press."},{"key":"983_CR51","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., & Caputo, B. (2004). Recognizing human actions: A local svm approach. In ICPR (pp. 32\u201336).","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"983_CR52","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Ali, S., & Shah, M. (2007). A 3-dimensional sift descriptor and its application to action recognition. In ACM Multimedia (pp. 357\u2013360).","DOI":"10.1145\/1291233.1291311"},{"issue":"5","key":"983_CR53","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1109\/TNNLS.2014.2330900","volume":"26","author":"L Shao","year":"2015","unstructured":"Shao, L., Zhu, F., & Li, X. (2015). Transfer learning for visual categorization: A survey. IEEE Transactions on Neural Networks and Learning Systems, 26(5), 1019\u20131034.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"983_CR54","unstructured":"Socher, R., Ganjoo, M., Manning, CD., & Ng, A. Y. (2013). Zero-shot learning through cross-modal transfer. In NIPS (pp. 935\u2013943)."},{"key":"983_CR55","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402"},{"key":"983_CR56","doi-asserted-by":"crossref","unstructured":"Wang, H., & Schmid, C. (2013). Action recognition with improved trajectories. In ICCV (pp. 3551\u20133558).","DOI":"10.1109\/ICCV.2013.441"},{"issue":"1","key":"983_CR57","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., & Liu, C. L. (2013). Dense trajectories and motion boundary descriptors for action recognition. International Journal of Computer Vision, 103(1), 60\u201379.","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"983_CR58","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang, H., Oneata, D., Verbeek, J., & Schmid, C. (2016). A robust and efficient video representation for action recognition. International Journal of Computer Vision, 119(3), 219\u2013238.","journal-title":"International Journal of Computer Vision"},{"key":"983_CR59","doi-asserted-by":"crossref","unstructured":"Wu, S., Bondugula, S., Luisier, F., Zhuang, X., & Natarajan, P. (2014). Zero-shot event detection using multi-modal fusion of weakly supervised concepts. In CVPR (pp. 2665\u20132672).","DOI":"10.1109\/CVPR.2014.341"},{"key":"983_CR60","doi-asserted-by":"crossref","unstructured":"Xu, X., Hospedales, T., & Gong, S. (2015). Semantic embedding space for zero shot action recognition. In ICIP (pp. 63\u201367).","DOI":"10.1109\/ICIP.2015.7350760"},{"key":"983_CR61","unstructured":"Yang, Y., & Hospedales, T. (2015). A unified perspective on multi-domain and multi-task learning. In ICLR."},{"key":"983_CR62","doi-asserted-by":"crossref","unstructured":"Yeffet, L., & Wolf, L. (2009). Local trinary patterns for human action recognition. In ICCV (pp. 492\u2013497).","DOI":"10.1109\/ICCV.2009.5459201"},{"key":"983_CR63","unstructured":"Zhao, F., Huang, Y., Wang, L., & Tan, T. (2013). Relevance topic model for unstructured social group activity recognition. In NIPS (pp. 2580\u20132588)."},{"key":"983_CR64","unstructured":"Zheng, J., & Jiang, Z. (2014). Submodular attribute selection for action recognition in video. In NIPS (pp. 1\u20139)."},{"key":"983_CR65","unstructured":"Zhou, D., Bousquet, O., & Weston, J. (2004). Learning with local and global consistency. In NIPS, (pp. 321\u2013328)."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-016-0983-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0983-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0983-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T03:37:14Z","timestamp":1658374634000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0983-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,10]]},"references-count":65,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,7]]}},"alternative-id":["983"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0983-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,10]]}}}