{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:02:45Z","timestamp":1773414165453,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819785100","type":"print"},{"value":"9789819785117","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8511-7_40","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:09:20Z","timestamp":1730524160000},"page":"570-583","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Species-Aware Guidance for Animal Action Recognition with Vision-Language Knowledge"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Zhai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qijun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keren","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"40_CR1","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":"40_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"40_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning, vol.\u00a02, p.\u00a04 (2021)"},{"key":"40_CR4","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"24","key":"40_CR5","doi-asserted-by":"publisher","first-page":"13596","DOI":"10.1073\/pnas.1922686117","volume":"117","author":"G Ceballos","year":"2020","unstructured":"Ceballos, G., Ehrlich, P.R., Raven, P.H.: Vertebrates on the brink as indicators of biological annihilation and the sixth mass extinction. Proc. Natl. Acad. Sci. 117(24), 13596\u201313602 (2020)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, M., Coker, D.J., Berumen, M.L., Costelloe, B., Beery, S., Rohrbach, A., Elhoseiny, M.: Mammalnet: A large-scale video benchmark for mammal recognition and behavior understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13052\u201313061 (2023)","DOI":"10.1109\/CVPR52729.2023.01254"},{"key":"40_CR7","unstructured":"Dai, X., Li, S., Zhao, Q., Yang, H.: Animal pose refinement in 2d images with 3d constraints. In: BMVC, p.\u00a0848 (2022)"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Dai, X., Li, S., Zhao, Q., Yang, H.: Unsupervised 3d animal canonical pose estimation with geometric self-supervision. In: 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG), pp.\u00a01\u20138. IEEE (2023)","DOI":"10.1109\/FG57933.2023.10042785"},{"key":"40_CR9","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":"40_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"issue":"2","key":"40_CR12","doi-asserted-by":"publisher","first-page":"485","DOI":"10.3390\/ani11020485","volume":"11","author":"L Feng","year":"2021","unstructured":"Feng, L., Zhao, Y., Sun, Y., Zhao, W., Tang, J.: Action recognition using a spatial-temporal network for wild felines. Animals 11(2), 485 (2021)","journal-title":"Animals"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Yan, X., Ji, G.P., Fu, K., Sun, M., Xiong, H., Fan, D.P., Khan, F.S.: Effectiveness assessment of recent large vision-language models. Vis. Intell. 2(17). https:\/\/link.springer.com\/article\/10.1007\/s44267-024-00050-1 (2024)","DOI":"10.1007\/s44267-024-00050-1"},{"key":"40_CR14","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: Temporal excitation and aggregation for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 909\u2013918 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C.Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., Feichtenhofer, C.: Mvitv2: Improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"40_CR17","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":"40_CR18","doi-asserted-by":"crossref","unstructured":"Liu, W., Li, Z., Tang, X.: Spatio-temporal embedding for statistical face recognition from video. In: Computer Vision\u2013ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7\u201313, 2006. Proceedings, Part II 9. pp. 374\u2013388. Springer (2006)","DOI":"10.1007\/11744047_29"},{"key":"40_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"40_CR20","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"40_CR21","unstructured":"Ma, X., Kaufhold, S., Su, J., Zhu, W., Terwilliger, J., Meza, A., Zhu, Y., Rossano, F., Wang, Y.: Chimpact: a longitudinal dataset for understanding chimpanzee behaviors. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Mondal, A., Nag, S., Prada, J.M., Zhu, X., Dutta, A.: Actor-agnostic multi-label action recognition with multi-modal query. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 784\u2013794 (2023)","DOI":"10.1109\/ICCVW60793.2023.00086"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Ng, X.L., Ong, K.E., Zheng, Q., Ni, Y., Yeo, S.Y., Liu, J.: Animal kingdom: a large and diverse dataset for animal behavior understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19023\u201319034 (2022)","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, H., Maclagan, S.J., Nguyen, T.D., Nguyen, T., Flemons, P., Andrews, K., Ritchie, E.G., Phung, D.: Animal recognition and identification with deep convolutional neural networks for automated wildlife monitoring. In: 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 40\u201349. IEEE (2017)","DOI":"10.1109\/DSAA.2017.31"},{"key":"40_CR25","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":"40_CR26","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: Crowdsourcing data collection for activity understanding. In: European Conference on Computer Vision, pp. 510\u2013526. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"40_CR28","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"40_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"40_CR31","unstructured":"Wang, M., Xing, J., Liu, Y.: Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472 (2021)"},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Wu, W., Wang, X., Luo, H., Wang, J., Yang, Y., Ouyang, W.: Bidirectional cross-modal knowledge exploration for video recognition with pre-trained vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6620\u20136630 (2023)","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"40_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zeng, Z., Zhao, Q., Zhai, Z.: Concap: contrastive context-aware prompt for resource-hungry action recognition. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 768\u2013773. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00137"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8511-7_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:15:46Z","timestamp":1730524546000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8511-7_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785100","9789819785117"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8511-7_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}