{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:46:29Z","timestamp":1743075989242,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785100"},{"type":"electronic","value":"9789819785117"}],"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_37","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:04:50Z","timestamp":1730523890000},"page":"525-539","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Video Representation of Vision-Language Model with Decoupled Explicit Temporal Modeling"],"prefix":"10.1007","author":[{"given":"Yuxi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sihong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 6816\u20136826 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"37_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning, pp. 813\u2013824 (2021)"},{"key":"37_CR3","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 200\u2013210 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6201\u20136210 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding. In: Proceedings of the European Conference on Computer Vision, pp. 105\u2013124 (2022)","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7082\u20137092 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3192\u20133201 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"37_CR10","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: Proceedings of the European Conference on Computer Vision, pp. 1\u201318 (2022)","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"37_CR11","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: St-adapter: parameter-efficient image-to-video transfer learning. In: Advances in Neural Information Processing Systems (2022)"},{"key":"37_CR12","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Rasheed, H.A., Khattak, M.U., Maaz, M., Khan, S.H., 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)","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"37_CR14","unstructured":"Ryoo, M.S., Piergiovanni, A.J., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: adaptive space-time tokenization for videos. In: Advances in Neural Information Processing Systems, pp. 12786\u201312797 (2021)"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L.D., 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":"37_CR16","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, B., Zhao, Z., Tong, Z., He, Y., Wang, Y., Wang, Y., Qiao, Y.: Videomae V2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14549\u201314560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"37_CR18","unstructured":"Wang, M., Xing, J., Liu, Y.: Actionclip: a new paradigm for video action recognition. arxiv:abs\/2109.08472 (2021)"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Wasim, S.T., Naseer, M., Khan, S.H., Khan, F.S., Shah, M.: Vita-clip: video and text adaptive CLIP via multimodal prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23034\u201323044 (2023)","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Wu, W., Sun, Z., Ouyang, W.: Revisiting classifier: transferring vision-language models for video recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2847\u20132855 (2023)","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, X., Arnab, A., Lu, Z., Zhang, M., Sun, C., Schmid, C.: Multiview transformers for video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3323\u20133333 (2022)","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"37_CR22","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: Aim: adapting image models for efficient video action recognition. In: International Conference on Learning Representations (2023)"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, X., Jia, J., Liu, S., Ding, K.: Text-visual prompting for efficient 2d temporal video grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14794\u201314804 (2023)","DOI":"10.1109\/CVPR52729.2023.01421"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: Actbert: learning global-local video-text representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8743\u20138752 (2020)","DOI":"10.1109\/CVPR42600.2020.00877"}],"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_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:15:02Z","timestamp":1730524502000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8511-7_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785100","9789819785117"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8511-7_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}