{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:19:11Z","timestamp":1783556351096,"version":"3.55.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032222633","type":"print"},{"value":"9783032222640","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-22264-0_15","type":"book-chapter","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:10:28Z","timestamp":1783555828000},"page":"186-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions"],"prefix":"10.1007","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuailong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxiao","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diying","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoran","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,2]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C.: Vivit: a video vision transformer. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, pp. 6816\u20136826 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"15_CR2","unstructured":"Ashutosh, K., Girdhar, R., Torresani, L., Grauman, K.: Hiervl: learning hierarchical video-language embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, p. 23,066\u201323,078"},{"key":"15_CR3","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"15_CR4","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"},{"key":"15_CR5","first-page":"10170","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Chen, D., Liu, R., et al.: Video action recognition with attentive semantic units. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10170\u201310180 (2023)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Huang, W., et al.: Hierarchical multi-label text classification: an attention-based recurrent network approach. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1051\u20131060","DOI":"10.1145\/3357384.3357885"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"issue":"5","key":"15_CR8","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","volume":"130","author":"Y Kong","year":"2022","unstructured":"Kong, Y., Fu, Y.: Human action recognition and prediction: a survey. Int. J. Comput. Vis. 130(5), 1366\u20131401 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"15_CR9","unstructured":"Li, K.: et al.: Videochat: Chat-centric video understanding. arXiv preprint https:\/\/arxiv.org\/abs\/2305.06355"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Li, T., et al.: Dynamic spatio-temporal specialization learning for fine-grained action recognition. In: European Conference on Computer Vision, pp. 386\u2013403","DOI":"10.1007\/978-3-031-19772-7_23"},{"key":"15_CR11","first-page":"1","volume-title":"European Conference on Computer Vision","author":"B Ni","year":"2022","unstructured":"Ni, B., et al.: Expanding language-image pretrained models for general video recognition. In: European Conference on Computer Vision, pp. 1\u201318. Springer Nature Switzerland, Cham (2022)"},{"key":"15_CR12","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, pp. 18\u201324"},{"key":"15_CR13","first-page":"6545","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"HA Rasheed","year":"2023","unstructured":"Rasheed, H.A., Khattak, M.U., Maaz, M., Khan, S., Khan, F.S.: Fine-tuned CLIP models are efficient video learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6545\u20136554 (2023)"},{"key":"15_CR14","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Proces. Syst. 27 (2014)"},{"key":"15_CR15","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint https:\/\/arxiv.org\/abs\/1212.0402"},{"key":"15_CR16","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human action recognition from various data modalities: a review. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3200\u20133225"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740\u20132755","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"15_CR18","unstructured":"Wang, M., Xing, J., Liu, Y.: Actionclip: A new paradigm for video action recognition. arXiv preprint. (2021). https:\/\/arxiv.org\/abs\/2109.08472"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-22264-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:10:30Z","timestamp":1783555830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-22264-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032222633","9783032222640"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-22264-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"42","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi25","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}