{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T17:49:52Z","timestamp":1776534592341,"version":"3.51.2"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T00:00:00Z","timestamp":1677715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T00:00:00Z","timestamp":1677715200000},"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":["Mach. Intell. Res."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s11633-022-1409-1","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T20:02:31Z","timestamp":1677787351000},"page":"249-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Compositional Prompting Video-language Models to Understand Procedure in Instructional Videos"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6198-8230","authenticated-orcid":false,"given":"Guyue","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3845-7335","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"issue":"2","key":"1409_CR1","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1348\/000709904X22403","volume":"75","author":"R J Nadolski","year":"2005","unstructured":"R. J. Nadolski, P. A. Kirschner, J. J. van Merri\u00ebnboer. Optimizing the number of steps in learning tasks for complex skills. British Journal of Educational Psychology, vol. 75, no. 2, pp. 223\u2013237, 2005. DOI: https:\/\/doi.org\/10.1348\/000709904X22403.","journal-title":"British Journal of Educational Psychology"},{"key":"1409_CR2","doi-asserted-by":"publisher","unstructured":"M. Rohrbach, S. Amin, M. Andriluka, B. Schiele. A database for fine grained activity detection of cooking activities. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, pp. 1194\u20131201, 2012. DOI: https:\/\/doi.org\/10.1109\/CVPR.2012.6247801.","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"1409_CR3","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1109\/CVPR.2019.00130","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y S Tang","year":"2019","unstructured":"Y. S. Tang, D. J. Ding, Y. M. Rao, Y. Zheng, D. Y. Zhang, L. L. Zhao, J. W. Lu, J. Zhou. COIN: A large-scale dataset for comprehensive instructional video analysis. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 1207\u20131216, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00130."},{"key":"1409_CR4","doi-asserted-by":"publisher","first-page":"5343","DOI":"10.1109\/CVPR.2018.00560","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y A Farha","year":"2018","unstructured":"Y. A. Farha, A. Richard, J. Gall. When will you do what? \u2014 Anticipating temporal occurrences of activities. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 5343\u20135352, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00560."},{"key":"1409_CR5","doi-asserted-by":"publisher","first-page":"3532","DOI":"10.1109\/CVPR.2019.00365","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"D Zhukov","year":"2019","unstructured":"D. Zhukov, J. B. Alayrac, R. G. Cinbis, D. Fouhey, I. Laptev, J. Sivic. Cross-task CVFweakly supervised learning from instructional videos. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 3532\u20133540, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00365."},{"key":"1409_CR6","doi-asserted-by":"publisher","unstructured":"H. Kuehne, A. Arslan, T. Serre. The language of actions: Recovering the syntax and semantics of goal-directed human activities. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, pp. 780\u2013787, 2014. DOI: https:\/\/doi.org\/10.1109\/CVPR.2014.105.","DOI":"10.1109\/CVPR.2014.105"},{"key":"1409_CR7","doi-asserted-by":"publisher","unstructured":"L. W. Zhou, C. L. Xu, J. J. Corso. Towards automatic learning of procedures from web instructional videos. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, USA, pp. 7590\u20137598, 2018. DOI: https:\/\/doi.org\/10.5555\/3504035.3504965.","DOI":"10.5555\/3504035.3504965"},{"key":"1409_CR8","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/978-3-030-58621-8_20","volume-title":"Proceedings of the 16th European Conference on Computer Vision","author":"C Y Chang","year":"2020","unstructured":"C. Y. Chang, D. A. Huang, D. F. Xu, E. Adeli, L. Fei-Fei, J. C. Niebles. Procedure planning in instructional videos. In Proceedings of the 16th European Conference on Computer Vision, Springer, Glasgow, UK, pp. 334\u2013350, 2020. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58621-8_20."},{"key":"1409_CR9","doi-asserted-by":"publisher","first-page":"8743","DOI":"10.1109\/CVPR42600.2020.00877","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L C Zhu","year":"2020","unstructured":"L. C. Zhu, Y. Yang. ActBERT: Learning global-local video-text representations. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 8743\u20138752, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00877."},{"key":"1409_CR10","doi-asserted-by":"publisher","unstructured":"C. Sun, A. Myers, C. Vondrick, K. Murphy, C. Schmid. VideoBERT: A joint model for video and language representation learning. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Repubic of Korea, pp.7463\u20137472, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00756.","DOI":"10.1109\/ICCV.2019.00756"},{"key":"1409_CR11","doi-asserted-by":"publisher","first-page":"9876","DOI":"10.1109\/CVPR42600.2020.00990","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Miech","year":"2020","unstructured":"A. Miech, J. B. Alayrac, L. Smaira, I. Laptev, J. Sivic, A. Zisserman. End-to-end learning of visual representations from uncurated instructional videos. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp.9876\u20139886, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00990."},{"key":"1409_CR12","doi-asserted-by":"publisher","unstructured":"B. Cui, G. Y. Hu, S. Yu. DeepCollaboration: Collaborative generative and discriminative models for class incremental learning. In Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp. 1175\u20131183, 2021. DOI: https:\/\/doi.org\/10.1609\/aaai.v35i2.16204.","DOI":"10.1609\/aaai.v35i2.16204"},{"key":"1409_CR13","doi-asserted-by":"publisher","first-page":"147560","DOI":"10.1109\/ACCESS.2019.2946425","volume":"7","author":"J P Zhang","year":"2019","unstructured":"J. P. Zhang, J. M. Zhang, G. Y. Hu, Y. Chen, S. Yu. Scalenet: A convolutional network to extract multi-scale and fine-grained visual features. IEEE Access, vol.7, pp.147560\u2013147570, 2019. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2019.2946425.","journal-title":"IEEE Access"},{"key":"1409_CR14","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, I. Polosukhin. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, pp. 6000\u20136010, 2017."},{"key":"1409_CR15","doi-asserted-by":"publisher","first-page":"2630","DOI":"10.1109\/ICCV.2019.00272","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"A Miech","year":"2019","unstructured":"A. Miech, D. Zhukov, J. B. Alayrac, M. Tapaswi, I. Laptev, J. Sivic. HowTo100m: Learning a text-video embedding by watching hundred million narrated video clips. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Seoul, Republic of Korea, pp. 2630\u20132640, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00272."},{"key":"1409_CR16","doi-asserted-by":"publisher","first-page":"9726","DOI":"10.1109\/CVPR42600.2020.00975","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K M He","year":"2020","unstructured":"K. M. He, H. Q. Fan, Y. X. Wu, S. N. Xie, R. Girshick. Momentum (contrast for unsupervised visual representation learning. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp.9726\u20139735, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00975."},{"key":"1409_CR17","doi-asserted-by":"publisher","unstructured":"G. Hu, B. Cui, S. Yu. Skeleton-based action recognition with synchronous local and non-local spatio-temporal learning and frequency attention. In Proceedings of IEEE International Conference on Multimedia and Expo, Shanghai, China, pp.1216\u20131221, 2019. DOI: https:\/\/doi.org\/10.1109\/ICME.2019.00212.","DOI":"10.1109\/ICME.2019.00212"},{"key":"1409_CR18","doi-asserted-by":"publisher","unstructured":"R. Goyal, S. E. Kahou, V. Michalski, J. Materzynska, S. Westphal, H. Kim, V. Haenel, I. Fruend, P. Yianilos, M. Mueller-Freitag, F. Hoppe, C. Thurau, I. Bax, R. Memisevic. The \u201csomething something\u201d video database for learning and evaluating visual common sense. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp.5843\u20135851, 2017. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.622.","DOI":"10.1109\/ICCV.2017.622"},{"issue":"9","key":"1409_CR19","doi-asserted-by":"publisher","first-page":"2207","DOI":"10.1109\/TMM.2019.2953325","volume":"22","author":"G Y Hu","year":"2020","unstructured":"G. Y. Hu, B. Cui, S. Yu. Joint learning in the spatio-temporal and frequency domains for skeleton-based action recognition. IEEE Transactions on Multimedia, vol. 22, no. 9, pp. 2207\u20132220, 2020. DOI: DOI: https:\/\/doi.org\/10.1109\/TMM.2019.2953325.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1409_CR20","doi-asserted-by":"publisher","unstructured":"F. C. Heilbron, V. Escorcia, B. Ghanem, J. C. Niebles. ActivityNet: A large-scale video benchmark for human activity understanding. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, pp. 961\u2013970, 2015. DOI: https:\/\/doi.org\/10.1109\/CVPR.2015.7298698.","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"1409_CR21","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1109\/CVPR42600.2020.00106","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"G Y Hu","year":"2020","unstructured":"G. Y. Hu, B. Cui, Y. He, S. Yu. Progressive relation learning for group activity recognition. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 977\u2013986, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00106."},{"issue":"3","key":"1409_CR22","doi-asserted-by":"publisher","first-page":"343","DOI":"10.24272\/j.issn.2095-8137.2021.353","volume":"43","author":"M S Liu","year":"2022","unstructured":"M. S. Liu, J. Q. Gao, G. Y. Hu, G. F. Hao, T. Z. Jiang, C. Zhang, S. Yu. MonkeyTrail: A scalable video-based method for tracking macaque movement trajectory in daily living cages. Zoological Research, vol. 43, no. 3, pp. 343\u2013351, 2022. DOI: https:\/\/doi.org\/10.24272\/j.issn.2095-8137.2021.353.","journal-title":"Zoological Research"},{"key":"1409_CR23","unstructured":"B. X. Wu, C. G. Yang, J. P. Zhong. Research on transfer learning of vision-based gesture recognition. [Online], Available: https:\/\/dblp.org\/rec\/journals\/corr\/abs-1812-05770.html?view=bibtex, 2021."},{"key":"1409_CR24","unstructured":"Z. W. Xu, X. J. Wu, J. Kittler. STRNet: Triple-stream spatiotemporal relation network for action recognition. [Online], Available: https:\/\/dblp.org\/rec\/conf\/cvpr\/WuGHFK20.html?view=bibtex, 2021."},{"issue":"3","key":"1409_CR25","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/s11633-020-1258-8","volume":"18","author":"L F Wu","year":"2021","unstructured":"L. F. Wu, Q. Wang, M. Jian, Y. Qiao, B. X. Zhao. A comprehensive review of group activity recognition in videos. International Journal of Automation and Computing, vol. 18, no. 3, pp. 334\u2013350, 2021. DOI: https:\/\/doi.org\/10.1007\/s11633-020-1258-8.","journal-title":"International Journal of Automation and Computing"},{"key":"1409_CR26","doi-asserted-by":"publisher","unstructured":"D. A. Huang, J. J. Lim, L. Fei-Fei, J. C. Niebles. Unsupervised visual-linguistic reference resolution in instructional videos. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 1032\u20131041, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.116.","DOI":"10.1109\/CVPR.2017.116"},{"key":"1409_CR27","doi-asserted-by":"publisher","first-page":"6057","DOI":"10.1109\/CVPR.2018.00634","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"H Doughty","year":"2018","unstructured":"H. Doughty, D. Damen, W. Mayol-Cuevas. Who\u2019s better? Who\u2019s best? Pairwise deep ranking for skill determination. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 6057\u20136066, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00634."},{"key":"1409_CR28","doi-asserted-by":"publisher","unstructured":"B. Singh, T. K. Marks, M. Jones, O. Tuzel, M. Shao. A multi-stream Bi-directional recurrent neural network for fine-grained action detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 1961\u20131970, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.216.","DOI":"10.1109\/CVPR.2016.216"},{"key":"1409_CR29","doi-asserted-by":"publisher","first-page":"3570","DOI":"10.1109\/CVPR.2019.00369","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y A Farha","year":"2019","unstructured":"Y. A. Farha, J. Gall. MS-TCN: Multi-stage temporal convolutional network for action segmentation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 3570\u20133579, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00369."},{"key":"1409_CR30","doi-asserted-by":"publisher","unstructured":"Y. Zhao, Y. J. Xiong, L. M. Wang, Z. R. Wu, X. O. Tang, D. H. Lin. Temporal action detection with structured segment networks. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp. 2933\u20132942, 2017. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.317.","DOI":"10.1109\/ICCV.2017.317"},{"key":"1409_CR31","doi-asserted-by":"publisher","unstructured":"H. J. Xu, A. Das, K. Saenko. R-C3D: Region convolutional 3D network for temporal activity detection. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp. 5794\u20135803, 2017. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.617.","DOI":"10.1109\/ICCV.2017.617"},{"key":"1409_CR32","doi-asserted-by":"publisher","first-page":"5987","DOI":"10.1109\/CVPR.2018.00627","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Richard","year":"2018","unstructured":"A. Richard, H. Kuehne, J. Gall. Action sets: Weakly supervised action segmentation without ordering constraints. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 5987\u20135996, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00627."},{"key":"1409_CR33","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/CVPR42600.2020.00095","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"H Doughty","year":"2020","unstructured":"H. Doughty, I. Laptev, W. Mayol-Cuevas, D. Damen. Action modifiers: Learning from adverbs in instructional videos. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 865\u2013875, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00095."},{"key":"1409_CR34","doi-asserted-by":"publisher","unstructured":"J. B. Alayrac, P. Bojanowski, N. Agrawal, J. Sivic, I. Laptev, S. Lacoste-Julien. Unsupervised learning from narrated instruction videos. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 4575\u20134583, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.495.","DOI":"10.1109\/CVPR.2016.495"},{"key":"1409_CR35","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1109\/CVPR.2019.00129","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S N Aakur","year":"2019","unstructured":"S. N. Aakur, S. Sarkar. A perceptual prediction framework for self supervised event segmentation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 1197\u20131206, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00129."},{"key":"1409_CR36","doi-asserted-by":"publisher","first-page":"12058","DOI":"10.1109\/CVPR.2019.01234","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Kukleva","year":"2019","unstructured":"A. Kukleva, H. Kuehne, F. Sener, J. Gall. Unsupervised learning of action classes with continuous temporal embedding. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 12058\u201312066, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.01234."},{"key":"1409_CR37","doi-asserted-by":"publisher","first-page":"8368","DOI":"10.1109\/CVPR.2018.00873","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"F Sener","year":"2018","unstructured":"F. Sener, A. Yao. Unsupervised learning and segmentation of complex activities from video. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 8368\u20138376, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00873."},{"issue":"3","key":"1409_CR38","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s11633-022-1331-6","volume":"19","author":"T X Sun","year":"2022","unstructured":"T. X. Sun, X. Y. Liu, X. P. Qiu, X. J. Huang. Paradigm shift in natural language processing. Machine Intelligence Research, vol. 19, no. 3, pp. 169\u2013183, 2022. DOI: https:\/\/doi.org\/10.1007\/s11633-022-1331-6.","journal-title":"Machine Intelligence Research"},{"key":"1409_CR39","unstructured":"A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever. Language models are unsupervised multitask learners. OpenAI blog, vol. 1, no. 8, Article number 9, 2019."},{"key":"1409_CR40","doi-asserted-by":"publisher","unstructured":"T. Schick, H. Sch\u00fctze. It\u2019s not just size that matters: Small language models are also few-shot learners. In Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2339\u20132352, 2021. DOI: https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.185.","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"key":"1409_CR41","doi-asserted-by":"publisher","unstructured":"X. L. Li, P. Liang. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 4582\u20134597, 2021. DOI: https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.353.","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"1409_CR42","unstructured":"P. F. Liu, W. Z. Yuan, J. L. Fu, Z. B. Jiang, H. Hayashi, G. Neubig. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. [Online], Available: https:\/\/arxiv.org\/abs\/2107.13586, 2021."},{"issue":"9","key":"1409_CR43","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Y Zhou","year":"2022","unstructured":"K. Y. Zhou, J. K. Yang, C. C. Loy, Z. W. Liu. Learning to prompt for vision-language models. International Journal of Computer Vision, vol. 130, no. 9, pp. 2337\u20132348, 2022. DOI: https:\/\/doi.org\/10.1007\/s11263-022-01653-1.","journal-title":"International Journal of Computer Vision"},{"key":"1409_CR44","unstructured":"Y. Yao, A. Zhang, Z. Y. Zhang, Z. Y. Liu, T. S. Chua, M. S. Sun. CPT: Colorful prompt tuning for pre-trained vision-language models. [Online], Available: https:\/\/arxiv.org\/abs\/2109.11797, 2021."},{"key":"1409_CR45","doi-asserted-by":"publisher","first-page":"16795","DOI":"10.1109\/CVPR52688.2022.01631","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K Y Zhou","year":"2022","unstructured":"K. Y. Zhou, J. K. Yang, C. C. Loy, Z. W. Liu. Conditional prompt learning for vision-language models. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 16795\u201316804, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01631."},{"key":"1409_CR46","unstructured":"M. M. Wang, J. Z. Xing, Y. Liu. ActionCLIP: A new paradigm for video action recognition. [Online], Available: https:\/\/arxiv.org\/abs\/2109.08472, 2021."},{"key":"1409_CR47","doi-asserted-by":"publisher","first-page":"18061","DOI":"10.1109\/CVPR52688.2022.01755","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y M Rao","year":"2022","unstructured":"Y. M. Rao, W. L. Zhao, G. Y. Chen, Y. S. Tang, Z. Zhu, G. Huang, J. Zhou, J. W. Lu. DenseCLIP: Language-guided dense prediction with context-aware prompting. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 18061\u201318070, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01755."},{"key":"1409_CR48","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-031-19833-5_7","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"C Ju","year":"2022","unstructured":"C. Ju, T. D. Han, K. H. Zheng, Y. Zhang, W. D. Xie. Prompting visual-language models for efficient video understanding. In Proceedings of the 17th European Conference on Computer Vision, Springer, Tel Aviv Israel, pp. 105\u2013124, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-19833-5_7."},{"issue":"4","key":"1409_CR49","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1177\/107769905303000401","volume":"30","author":"W L Taylor","year":"1953","unstructured":"W. L. Taylor. \u201cCloze procedure\u201d: A new tool for measuring readability. Journalism Quarterly, vol. 30, no. 4, pp. 415\u2013433, 1953. DOI: https:\/\/doi.org\/10.1177\/107769905303000401.","journal-title":"Journalism Quarterly"},{"key":"1409_CR50","doi-asserted-by":"publisher","unstructured":"J. Devlin, M. W. Chang, K. Lee, K. Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, USA, pp. 4171\u20134186, 2019. DOI: https:\/\/doi.org\/10.18653\/v1\/N19-1423.","DOI":"10.18653\/v1\/N19-1423"},{"key":"1409_CR51","doi-asserted-by":"crossref","unstructured":"Z. Gan, L. J. Li, C. Y. Li, L. J. Wang, Z. C. Liu, J. F. Gao. Vision-language pre-training: Basics, recent advances, and future trends. [Online], Available: https:\/\/arxiv.org\/abs\/2210.09263, 2022.","DOI":"10.1561\/9781638281337"},{"key":"1409_CR52","unstructured":"F. L. Chen, D. Z. Zhang, M. L. Han, X. Y. Chen, J. Shi, S. Xu, B. Xu. VLP: A survey on vision-language pre-training. [Online], Available: https:\/\/arxiv.org\/abs\/2202.09061, 2022."},{"key":"1409_CR53","unstructured":"A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, I. Sutskever. Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763, 2021."},{"key":"1409_CR54","doi-asserted-by":"publisher","unstructured":"T. Shin, Y. Razeghi, R. L. Logan IV, E. Wallace, S. Singh. AutoPrompt: Eliciting knowledge from language models with automatically generated prompts. In Proceedings of Conference on Empirical Methods in Natural Language Processing, pp. 4222\u20134235, 2020. DOI: https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.346.","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"1409_CR55","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01225-0_1","volume-title":"Proceedings of the 15th European Conference on Computer Vision","author":"T W Lin","year":"2018","unstructured":"T. W. Lin, X. Zhao, H. S. Su, C. J. Wang, M. Yang. BSN: Boundary sensitive network for temporal action proposal generation. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 3\u201321, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1."},{"key":"1409_CR56","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1109\/CVPR52688.2022.00101","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S C Wang","year":"2022","unstructured":"S. C. Wang, Y. Q. Duan, H. H. Ding, Y. P. Tan, K. H. Yap, J. S. Yuan. Learning transferable human-object interaction detector with natural language supervision. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 929\u2013938, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00101."},{"key":"1409_CR57","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Proceedings of the 15th European Conference on Computer Vision","author":"S N Xie","year":"2018","unstructured":"S. N. Xie, C. Sun, J. Huang, Z. W. Tu, K. Murphy. Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 318\u2013335, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19."},{"key":"1409_CR58","unstructured":"T. Mikolov, K. Chen, G. Corrado, J. Dean. Efficient estimation of word representations in vector space. [Online], Available: https:\/\/arxiv.org\/abs\/1301.3781, 2013."},{"key":"1409_CR59","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Proceedings of the 14th European Conference on Computer Vision","author":"L M Wang","year":"2016","unstructured":"L. M. Wang, Y. J. Xiong, Z. Wang, Y. Qiao, D. H. Lin, X. O. Tang, L. van Gool. Temporal segment networks: Towards good practices for deep action recognition. In Proceedings of the 14th European Conference on Computer Vision, Springer, Amsterdam, The Netherlands, pp. 20\u201336, 2016. DOI: https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2."},{"key":"1409_CR60","doi-asserted-by":"publisher","first-page":"7082","DOI":"10.1109\/ICCV.2019.00718","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"J Lin","year":"2019","unstructured":"J. Lin, C. Gan, S. Han. TSM: Temporal shift module for efficient video understanding. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Seoul, Repubic of Korea, pp. 7082\u20137092, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00718."},{"key":"1409_CR61","doi-asserted-by":"publisher","first-page":"2000","DOI":"10.1109\/ICCV.2019.00209","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"B Y Jiang","year":"2019","unstructured":"B. Y. Jiang, M. M. Wang, W. H. Gan, W. Wu, J. J. Yan. STM: Spatiotemporal and motion encoding for action recognition. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Seoul, Repubic of Korea, pp. 2000\u20132009, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00209."},{"key":"1409_CR62","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1109\/CVPR46437.2021.00193","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L M Wang","year":"2021","unstructured":"L. M. Wang, Z. Tong, B. Ji, G. S. Wu. TDN: Temporal difference networks for efficient action recognition. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, pp. 1895\u20131904, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.00193."},{"key":"1409_CR63","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1007\/978-3-030-58526-6_28","volume-title":"Proceedings of the 16th European Conference on Computer Vision","author":"D Zhukov","year":"2020","unstructured":"D. Zhukov, J. B. Alayrac, I. Laptev, J. Sivic. Learning actionness via long-range temporal order verification. In Proceedings of the 16th European Conference on Computer Vision, Springer, Glasgow, UK, pp. 470\u2013487, 2020. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58526-6_28."},{"key":"1409_CR64","doi-asserted-by":"publisher","first-page":"9866","DOI":"10.1109\/CVPR42600.2020.00989","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"D D Shan","year":"2020","unstructured":"D. D. Shan, J. Q. Geng, M. Shu, D. F. Fouhey. Understanding human hands in contact at internet scale. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 9866\u20139875, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00989."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-022-1409-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-022-1409-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-022-1409-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T06:20:10Z","timestamp":1720678810000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-022-1409-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,2]]},"references-count":64,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["1409"],"URL":"https:\/\/doi.org\/10.1007\/s11633-022-1409-1","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,2]]},"assertion":[{"value":"30 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}