{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:24:50Z","timestamp":1783041890799,"version":"3.54.6"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"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":["SOCA"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11761-025-00468-5","type":"journal-article","created":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T11:58:42Z","timestamp":1753531122000},"page":"215-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TSAVD-CLIP: One visual encoder learn both temporal and spatial feat"],"prefix":"10.1007","volume":"20","author":[{"given":"Xu","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaxiao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingxin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2784-6607","authenticated-orcid":false,"given":"Yuxiang","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"468_CR1","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6479\u20136488 (2018)","DOI":"10.1109\/CVPR.2018.00678"},{"key":"468_CR2","doi-asserted-by":"crossref","unstructured":"Zaheer, M.Z., Mahmood, A., Astrid, M., Lee, S.-I.: Claws: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXII 16, pp. 358\u2013376 (2020). Springer","DOI":"10.1007\/978-3-030-58542-6_22"},{"key":"468_CR3","doi-asserted-by":"crossref","unstructured":"Cho, M., Kim, M., Hwang, S., Park, C., Lee, K., Lee, S.: Look around for anomalies: Weakly-supervised anomaly detection via context-motion relational learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12137\u201312146 (2023)","DOI":"10.1109\/CVPR52729.2023.01168"},{"key":"468_CR4","doi-asserted-by":"crossref","unstructured":"Zhou, H., Yu, J., Yang, W.: Dual memory units with uncertainty regulation for weakly supervised video anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37 (2023)","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"468_CR5","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1609\/aaai.v36i2.20028","volume":"36","author":"S Li","year":"2022","unstructured":"Li S, Liu F, Jiao L (2022) Self-training multi-sequence learning with transformer for weakly supervised video anomaly detection. In Proceedings of the AAAI Conference on Artificial Intelligence 36:1395\u20131403","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"468_CR6","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1609\/aaai.v37i1.25112","volume":"37","author":"Y Chen","year":"2023","unstructured":"Chen Y, Liu Z, Zhang B, Fok W, Qi X, Wu Y-C (2023) Mgfn: Magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection. In Proceedings of the AAAI Conference on Artificial Intelligence 37:387\u2013395","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"468_CR7","doi-asserted-by":"crossref","unstructured":"Lv, H., et\u00a0al.: Unbiased multiple instance learning for weakly supervised video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"468_CR8","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, J., Wu, P.: Text prompt with normality guidance for weakly supervised video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01788"},{"key":"468_CR9","doi-asserted-by":"crossref","unstructured":"Wu, P., Li, J., Zhang, W., Wang, F.: Weakly supervised video anomaly detection and localization with spatio-temporal prompts. In: Proceedings of the 32nd ACM International Conference on Multimedia (2024)","DOI":"10.1145\/3664647.3681442"},{"key":"468_CR10","unstructured":"Wu, P., et al.: Deep learning for video anomaly detection: A review. arXiv preprint arXiv:2409.05383 (2024)"},{"key":"468_CR11","doi-asserted-by":"crossref","unstructured":"Tian, Y., et\u00a0al.: Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00493"},{"issue":"6","key":"468_CR12","doi-asserted-by":"publisher","first-page":"6074","DOI":"10.1609\/aaai.v38i6.28423","volume":"38","author":"P Wu","year":"2024","unstructured":"Wu P et al (2024) Vadclip: Adapting vision-language models for weakly supervised video anomaly detection. Proceedings of the AAAI Conference on Artificial Intelligence 38(6):6074\u20136082","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"468_CR13","doi-asserted-by":"crossref","unstructured":"Wu, P., et\u00a0al.: Weakly supervised video anomaly detection and localization with spatio-temporal prompts. In: Proceedings of the 32nd ACM International Conference on Multimedia (2024)","DOI":"10.1145\/3664647.3681442"},{"key":"468_CR14","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research (PMLR) (2021)"},{"key":"468_CR15","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De\u00a0Laroussilhe, Q., Gesmundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for nlp. In: International Conference on Machine Learning, pp. 2790\u20132799 (2019). PMLR"},{"key":"468_CR16","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., Kamath, A., R\u00fcckl\u00e9, A., Cho, K., Gurevych, I.: Adapterfusion: Non-destructive task composition for transfer learning. arXiv preprint arXiv:2005.00247 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"issue":"2","key":"468_CR17","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao P, Geng S, Zhang R, Ma T, Fang R, Zhang Y, Li H, Qiao Y (2024) Clip-adapter: Better vision-language models with feature adapters. Int J Comput Vision 132(2):581\u2013595","journal-title":"Int J Comput Vision"},{"issue":"2","key":"468_CR18","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W et al (2022) Lora: Low-rank adaptation of large language models. ICLR 1(2):3","journal-title":"ICLR"},{"key":"468_CR19","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: Aim: Adapting image models for efficient video action recognition. arXiv preprint arXiv:2302.03024 (2023)"},{"key":"468_CR20","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"468_CR21","unstructured":"Sch\u00f6lkopf, B., Williamson, R.C., Smola, A., Shawe-Taylor, J., Platt, J.: Support vector method for novelty detection. Advances in neural information processing systems 12 (1999)"},{"key":"468_CR22","doi-asserted-by":"crossref","unstructured":"Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A.K., Davis, L.S.: Learning temporal regularity in video sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 733\u2013742 (2016)","DOI":"10.1109\/CVPR.2016.86"},{"key":"468_CR23","doi-asserted-by":"crossref","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXV, pp. 105\u2013124 (2022). Springer","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"468_CR24","doi-asserted-by":"crossref","unstructured":"Wu, P., Liu, J., Shi, Y., Sun, Y., Shao, F., Wu, Z., Yang, Z.: Not only look, but also listen: Learning multimodal violence detection under weak supervision. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXX 16, pp. 322\u2013339 (2020). Springer","DOI":"10.1007\/978-3-030-58577-8_20"}],"container-title":["Service Oriented Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11761-025-00468-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11761-025-00468-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11761-025-00468-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T05:26:56Z","timestamp":1780118816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11761-025-00468-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,26]]},"references-count":24,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["468"],"URL":"https:\/\/doi.org\/10.1007\/s11761-025-00468-5","relation":{},"ISSN":["1863-2386","1863-2394"],"issn-type":[{"value":"1863-2386","type":"print"},{"value":"1863-2394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,26]]},"assertion":[{"value":"5 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}