{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T14:16:14Z","timestamp":1785939374270,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":51,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819541089","type":"print"},{"value":"9789819541096","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"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\/978-981-95-4109-6_29","type":"book-chapter","created":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T20:14:33Z","timestamp":1763324073000},"page":"428-442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GMFVAD: Using Grained Multi-modal Feature to\u00a0Improve Video Anomaly Detection"],"prefix":"10.1007","author":[{"given":"Guangyu","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Abati, D., Porrello, A., Calderara, S., Cucchiara, R.: Latent space autoregression for novelty detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 481\u2013490 (2019)","DOI":"10.1109\/CVPR.2019.00057"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Acsintoae, A., et al.: Ubnormal: new benchmark for supervised open-set video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20143\u201320153 (2022)","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Astrid, M., Zaheer, M.Z., Lee, J.Y., Lee, S.I.: Learning not to reconstruct anomalies. arXiv preprint arXiv:2110.09742 (2021)","DOI":"10.5244\/C.35.205"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Bakkali, S., Ming, Z., Coustaty, M., Rusi\u00f1ol, M.: Visual and textual deep feature fusion for document image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 562\u2013563 (2020)","DOI":"10.1109\/CVPRW50498.2020.00289"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Basharat, A., Gritai, A., Shah, M.: Learning object motion patterns for anomaly detection and improved object detection. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587510"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD\u2013a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9592\u20139600 (2019)","DOI":"10.1109\/CVPR.2019.00982"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Burlina, P., Joshi, N., Wang, I.J.: Where\u2019s wally now? Deep generative and discriminative embeddings for novelty detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.01177"},{"key":"29_CR8","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":"29_CR9","doi-asserted-by":"publisher","first-page":"4067","DOI":"10.1109\/TMM.2021.3112814","volume":"24","author":"S Chang","year":"2021","unstructured":"Chang, S., Li, Y., Shen, S., Feng, J., Zhou, Z.: Contrastive attention for video anomaly detection. IEEE Trans. Multimedia 24, 4067\u20134076 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Chen, W., Ma, K.T., Yew, Z.J., Hur, M., Khoo, D.A.A.: TEVAD: improved video anomaly detection with captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5548\u20135558 (2023)","DOI":"10.1109\/CVPRW59228.2023.00587"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, Z., Zhang, B., Fok, W., Qi, X., Wu, Y.C.: MGFN: magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 387\u2013395 (2023)","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Feng, J.C., Hong, F.T., Zheng, W.S.: MIST: multiple instance self-training framework for video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14009\u201314018 (2021)","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Georgescu, M.I., Barbalau, A., Ionescu, R.T., Khan, F.S., Popescu, M., Shah, M.: Anomaly detection in video via self-supervised and multi-task learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12742\u201312752 (2021)","DOI":"10.1109\/CVPR46437.2021.01255"},{"issue":"9","key":"29_CR14","first-page":"4505","volume":"44","author":"MI Georgescu","year":"2021","unstructured":"Georgescu, M.I., Ionescu, R.T., Khan, F.S., Popescu, M., Shah, M.: A background-agnostic framework with adversarial training for abnormal event detection in video. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 4505\u20134523 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Gong, D., et al.: Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1705\u20131714 (2019)","DOI":"10.1109\/ICCV.2019.00179"},{"key":"29_CR16","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":"29_CR17","doi-asserted-by":"crossref","unstructured":"Ionescu, R.T., Khan, F.S., Georgescu, M.I., Shao, L.: Object-centric auto-encoders and dummy anomalies for abnormal event detection in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7842\u20137851 (2019)","DOI":"10.1109\/CVPR.2019.00803"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Joo, H.K., Vo, K., Yamazaki, K., Le, N.: CLIP-TSA: CLIP-assisted temporal self-attention for weakly-supervised video anomaly detection. In: 2023 IEEE International Conference on Image Processing (ICIP), pp. 3230\u20133234. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"29_CR19","unstructured":"Kay, W., Carreira, J., Simonyan, K., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., Liu, F., Jiao, L.: Self-training multi-sequence learning with transformer for weakly supervised video anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1395\u20131403 (2022)","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Lin, K., et al.: SwinBERT: end-to-end transformers with sparse attention for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17949\u201317958 (2022)","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Liu, W., Luo, W., Lian, D., Gao, S.: Future frame prediction for anomaly detection\u2013a new baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6536\u20136545 (2018)","DOI":"10.1109\/CVPR.2018.00684"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Lv, H., Yue, Z., Sun, Q., Luo, B., Cui, Z., Zhang, H.: Unbiased multiple instance learning for weakly supervised video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8022\u20138031 (2023)","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"29_CR24","doi-asserted-by":"publisher","first-page":"4505","DOI":"10.1109\/TIP.2021.3072863","volume":"30","author":"H Lv","year":"2021","unstructured":"Lv, H., Zhou, C., Cui, Z., Xu, C., Li, Y., Yang, J.: Localizing anomalies from weakly-labeled videos. IEEE Trans. Image Process. 30, 4505\u20134515 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"29_CR25","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1109\/34.946990","volume":"23","author":"G Medioni","year":"2001","unstructured":"Medioni, G., Cohen, I., Br\u00e9mond, F., Hongeng, S., Nevatia, R.: Event detection and analysis from video streams. IEEE Trans. Pattern Anal. Mach. Intell. 23(8), 873\u2013889 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR26","unstructured":"Nguyen, D.T., Lou, Z., Klar, M., Brox, T.: Anomaly detection with multiple-hypotheses predictions. In: International Conference on Machine Learning, pp. 4800\u20134809. PMLR (2019)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen, T.N., Meunier, J.: Anomaly detection in video sequence with appearance-motion correspondence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1273\u20131283 (2019)","DOI":"10.1109\/ICCV.2019.00136"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Panariello, A., Porrello, A., Calderara, S., Cucchiara, R.: Consistency-based self-supervised learning for temporal anomaly localization. In: European Conference on Computer Vision, pp. 338\u2013349. Springer (2022)","DOI":"10.1007\/978-3-031-25072-9_22"},{"key":"29_CR29","unstructured":"Paszke, A., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"29_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Sapkota, H., Yu, Q.: Bayesian nonparametric submodular video partition for robust anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3212\u20133221 (2022)","DOI":"10.1109\/CVPR52688.2022.00321"},{"key":"29_CR32","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":"29_CR33","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Hawk: learning to understand open-world video anomalies. In: Advances in Neural Information Processing Systems, vol. 37, pp. 139751\u2013139785 (2024)","DOI":"10.52202\/079017-4435"},{"key":"29_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/978-3-030-59725-2_27","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"Yu Tian","year":"2020","unstructured":"Tian, Yu., Maicas, G., Pu, L.Z.C.T., Singh, R., Verjans, J.W., Carneiro, G.: Few-shot anomaly detection for polyp frames from colonoscopy. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 274\u2013284. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59725-2_27"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J.W., Carneiro, G.: Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4975\u20134986 (2021)","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"29_CR36","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"},{"issue":"11","key":"29_CR37","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740\u20132755 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: VATEX: a large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"29_CR39","doi-asserted-by":"publisher","first-page":"3513","DOI":"10.1109\/TIP.2021.3062192","volume":"30","author":"P Wu","year":"2021","unstructured":"Wu, P., Liu, J.: Learning causal temporal relation and feature discrimination for anomaly detection. IEEE Trans. Image Process. 30, 3513\u20133527 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"29_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-3-030-58577-8_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Wu","year":"2020","unstructured":"Wu, P., et al.: Not only look, but also listen: learning multimodal violence detection under weak supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 322\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20"},{"key":"29_CR41","doi-asserted-by":"publisher","first-page":"1674","DOI":"10.1109\/TMM.2022.3147369","volume":"25","author":"P Wu","year":"2022","unstructured":"Wu, P., Liu, X., Liu, J.: Weakly supervised audio-visual violence detection. IEEE Trans. Multimedia 25, 1674\u20131685 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Wu, P., et al.: Open-vocabulary video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18297\u201318307, June 2024","DOI":"10.1109\/CVPR52733.2024.01732"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Wu, P., et al.: Weakly supervised video anomaly detection and localization with spatio-temporal prompts. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 9301\u20139310 (2024)","DOI":"10.1145\/3664647.3681442"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Wu, P., et al.: VadCLIP: adapting vision-language models for weakly supervised video anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 6074\u20136082 (2024)","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, T., Zhang, X., Liu, B., Liu, K., Jin, J., Jiao, Z.: Surveillance video-and-language understanding: from small to large multimodal models. IEEE Trans. Circuits Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3462433"},{"key":"29_CR46","unstructured":"Zaheer, M.Z., Lee, J.H., Astrid, M., Lee, S.I.: Old is gold: redefining the adversarially learned one-class classifier training paradigm. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14183\u201314193 (2020)"},{"key":"29_CR47","unstructured":"Zhang, H., et al.: Holmes-VAD: towards unbiased and explainable video anomaly detection via multi-modal LLM. arXiv preprint arXiv:2406.12235 (2024)"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, J., Qing, L., Miao, J.: Temporal convolutional network with complementary inner bag loss for weakly supervised anomaly detection. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 4030\u20134034. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803657"},{"key":"29_CR49","doi-asserted-by":"crossref","unstructured":"Zhong, J.X., Li, N., Kong, W., Liu, S., Li, T.H., Li, G.: Graph convolutional label noise cleaner: train a plug-and-play action classifier for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1237\u20131246 (2019)","DOI":"10.1109\/CVPR.2019.00133"},{"key":"29_CR50","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.\u00a037, pp. 3769\u20133777 (2023)","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"29_CR51","unstructured":"Zong, B., et al.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4109-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:50:46Z","timestamp":1785840646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4109-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"ISBN":["9789819541089","9789819541096"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4109-6_29","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"17 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}