{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:17:50Z","timestamp":1784179070623,"version":"3.55.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200618","type":"print"},{"value":"9783031200625","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20062-5_39","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:31:55Z","timestamp":1668076315000},"page":"681-697","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Zero-Shot Temporal Action Detection via\u00a0Vision-Language Prompting"],"prefix":"10.1007","author":[{"given":"Sauradip","family":"Nag","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"39_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/978-3-030-01219-9_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Alwassel","year":"2018","unstructured":"Alwassel, H., Caba Heilbron, F., Escorcia, V., Ghanem, B.: Diagnosing error in temporal action detectors. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 264\u2013280. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_16"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Vqa: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-nms-improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561\u20135569 (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"39_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"39_CR6","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 Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: attention over convolution kernels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11030\u201311039 (2020)","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"39_CR8","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"39_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: Ms-tcn: multi-stage temporal convolutional network for action segmentation. In: CVPR, pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Chen, K., Sun, C., Nevatia, R.: Turn tap: temporal unit regression network for temporal action proposals. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"39_CR12","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. arXiv preprint. arXiv:2110.04544 (2021)"},{"key":"39_CR13","unstructured":"Goldberg, Y., Levy, O.: word2vec explained: deriving mikolov et al\u2019.s negative-sampling word-embedding method. arXiv preprint. arXiv:1402.3722 (2014)"},{"key":"39_CR14","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":"39_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","unstructured":"Idrees, H.: The thumos challenge on action recognition for videos \u201cin the wild\u2019\u2019. Comput. Vis. Image Underst. 155, 1\u201323 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"39_CR16","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"39_CR17","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: A simple baseline on prompt learning for efficient video understanding (2022)"},{"issue":"3","key":"39_CR18","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1109\/TPAMI.2013.140","volume":"36","author":"CH Lampert","year":"2013","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453\u2013465 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: clipbert for video-and-language learning via sparse sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7331\u20137341 (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: Bmn: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"39_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01225-0_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Lin","year":"2018","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 3\u201321. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"key":"39_CR23","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9879\u20139889 (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 4th International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"39_CR26","unstructured":"Nag, S., Zhu, X., Song, Y.Z., Xiang, T.: Temporal action localization with global segmentation mask transformers (2021)"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Nag, S., Zhu, X., Song, Y.z., Xiang, T.: Proposal-free temporal action detection via global segmentation mask learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20062-5_37"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Nag, S., Zhu, X., Song, Y.z., Xiang, T.: Semi-supervised temporal action detection with proposal-free masking. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20062-5_38"},{"key":"39_CR29","unstructured":"Nag, S., Zhu, X., Xiang, T.: Few-shot temporal action localization with query adaptive transformer. arXiv preprint. arXiv:2110.10552 (2021)"},{"issue":"2","key":"39_CR30","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1109\/TIP.2018.2872916","volume":"28","author":"L Niu","year":"2018","unstructured":"Niu, L., Cai, J., Veeraraghavan, A., Zhang, L.: Zero-shot learning via category-specific visual-semantic mapping and label refinement. IEEE Trans. Image Process. 28(2), 965\u2013979 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"39_CR31","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: Parameter-efficient image-to-video transfer learning. arXiv preprint. arXiv:2206.13559 (2022)"},{"key":"39_CR32","doi-asserted-by":"crossref","unstructured":"Parikh, D., Grauman, K.: Relative attributes. In: 2011 International Conference on Computer Vision, pp. 503\u2013510. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"39_CR33","doi-asserted-by":"publisher","first-page":"8886","DOI":"10.1109\/TIP.2021.3120038","volume":"30","author":"S Paul","year":"2021","unstructured":"Paul, S., Mithun, N.C., Roy-Chowdhury, A.K.: Text-based localization of moments in a video corpus. IEEE Trans. Image Process. 30, 8886\u20138899 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"39_CR35","doi-asserted-by":"crossref","unstructured":"Qin, J., et al.: 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":"39_CR36","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"39_CR37","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: Denseclip: language-guided dense prediction with context-aware prompting. arXiv preprint. arXiv:2112.01518 (2021)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"39_CR38","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: TPAMI, vol. 39, no. 6, pp. 1137\u20131149 (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"39_CR39","doi-asserted-by":"crossref","unstructured":"Sridhar, D., Quader, N., Muralidharan, S., Li, Y., Dai, P., Lu, J.: Class semantics-based attention for action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13739\u201313748 (2021)","DOI":"10.1109\/ICCV48922.2021.01348"},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Su, H., Gan, W., Wu, W., Qiao, Y., Yan, J.: Bsn++: complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation. arXiv preprint. arXiv:2009.07641 (2020)","DOI":"10.1609\/aaai.v35i3.16363"},{"key":"39_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint. arXiv:1706.03762 (2017)"},{"key":"39_CR42","unstructured":"Wang, M., Xing, J., Liu, Y.: Actionclip: a new paradigm for video action recognition. arXiv preprint. arXiv:2109.08472 (2021)"},{"key":"39_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Camp: cross-modal adaptive message passing for text-image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"issue":"9","key":"39_CR44","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","volume":"41","author":"Y Xian","year":"2018","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2251\u20132265 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR45","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-c3d: region convolutional 3d network for temporal activity detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"39_CR46","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"39_CR47","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-tad: sub-graph localization for temporal action detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"39_CR48","doi-asserted-by":"crossref","unstructured":"Xu, X., Hospedales, T., Gong, S.: Semantic embedding space for zero-shot action recognition. In: 2015 IEEE International Conference on Image Processing (ICIP), pp. 63\u201367. IEEE (2015)","DOI":"10.1109\/ICIP.2015.7350760"},{"key":"39_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: Zstad: zero-shot temporal activity detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 879\u2013888 (2020)","DOI":"10.1109\/CVPR42600.2020.00096"},{"key":"39_CR50","unstructured":"Zhang, R., et al.: Tip-adapter: training-free clip-adapter for better vision-language modeling. arXiv preprint. arXiv:2111.03930 (2021)"},{"key":"39_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, C., Thabet, A.K., Ghanem, B.: Video self-stitching graph network for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13658\u201313667 (2021)","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"39_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"39_CR53","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: Regionclip: Region-based language-image pretraining. arXiv preprint. arXiv:2112.09106 (2021)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"39_CR54","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. arXiv preprint. arXiv:2109.01134 (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20062-5_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:23:58Z","timestamp":1668126238000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20062-5_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200618","9783031200625"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20062-5_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","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":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}