{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:59:03Z","timestamp":1743015543987,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620708"},{"type":"electronic","value":"9789819620715"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-2071-5_28","type":"book-chapter","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T15:34:29Z","timestamp":1735745669000},"page":"383-397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Anomaly Detection in\u00a03D Motion Through Language-Inspired Occlusion-Aware Modeling"],"prefix":"10.1007","author":[{"given":"Su","family":"Li","sequence":"first","affiliation":[]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jianye","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ziheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Junjun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,2]]},"reference":[{"unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)","key":"28_CR1"},{"doi-asserted-by":"crossref","unstructured":"Arnab, A., Doersch, C., Zisserman, A.: Exploiting temporal context for 3d human pose estimation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3395\u20133404 (2019)","key":"28_CR2","DOI":"10.1109\/CVPR.2019.00351"},{"doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Chang, J.Y., Lee, K.M.: Beyond static features for temporally consistent 3d human pose and shape from a video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1964\u20131973 (2021)","key":"28_CR3","DOI":"10.1109\/CVPR46437.2021.00200"},{"doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Lee, K.M.: Pose2mesh: graph convolutional network for 3d human pose and mesh recovery from a 2d human pose. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII 16, pp. 769\u2013787. Springer (2020)","key":"28_CR4","DOI":"10.1007\/978-3-030-58571-6_45"},{"unstructured":"Contributors, M.: MMFlow: Openmmlab optical flow toolbox and benchmark (2021). https:\/\/github.com\/open-mmlab\/mmflow","key":"28_CR5"},{"unstructured":"Degardin, B.M.: Weakly and partially supervised learning frameworks for anomaly detection. Master\u2019s thesis, Universidade da Beira Interior (Portugal) (2020)","key":"28_CR6"},{"doi-asserted-by":"crossref","unstructured":"Ding, M., Wang, Z., Zhou, B., Shi, J., Lu, Z., Luo, P.: Every frame counts: joint learning of video segmentation and optical flow. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 10713\u201310720 (2020)","key":"28_CR7","DOI":"10.1609\/aaai.v34i07.6699"},{"doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","key":"28_CR8","DOI":"10.1109\/ICCV.2015.316"},{"unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Advances in neural information processing systems 27 (2014)","key":"28_CR9"},{"doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., Cheng, L.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5152\u20135161, June 2022","key":"28_CR10","DOI":"10.1109\/CVPR52688.2022.00509"},{"issue":"8","key":"28_CR11","doi-asserted-by":"publisher","first-page":"3618","DOI":"10.1109\/JBHI.2021.3122463","volume":"26","author":"Y Hao","year":"2021","unstructured":"Hao, Y., Tang, Z., Alzahrani, B., Alotaibi, R., Alharthi, R., Zhao, M., Mahmood, A.: An end-to-end human abnormal behavior recognition framework for crowds with mentally disordered individuals. IEEE J. Biomed. Health Inform. 26(8), 3618\u20133625 (2021)","journal-title":"IEEE J. Biomed. Health Inform."},{"doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (jul 2014)","key":"28_CR12","DOI":"10.1109\/TPAMI.2013.248"},{"unstructured":"Ji, X., Zhao, S., Li, J.: An algorithm for abnormal behavior recognition based on sharing human target tracking features. International Journal of Intelligent Robotics and Applications, pp. 1\u201313 (2024)","key":"28_CR13"},{"doi-asserted-by":"crossref","unstructured":"Jiang, S., Campbell, D., Lu, Y., Li, H., Hartley, R.: Learning to estimate hidden motions with global motion aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9772\u20139781 (2021)","key":"28_CR14","DOI":"10.1109\/ICCV48922.2021.00963"},{"doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","key":"28_CR15","DOI":"10.1109\/CVPR.2018.00744"},{"doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3d human dynamics from video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5614\u20135623 (2019)","key":"28_CR16","DOI":"10.1109\/CVPR.2019.00576"},{"doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: video inference for human body pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253\u20135263 (2020)","key":"28_CR17","DOI":"10.1109\/CVPR42600.2020.00530"},{"doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: Pare: part attention regressor for 3d human body estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11127\u201311137 (2021)","key":"28_CR18","DOI":"10.1109\/ICCV48922.2021.01094"},{"doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3d human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2252\u20132261 (2019)","key":"28_CR19","DOI":"10.1109\/ICCV.2019.00234"},{"doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: Hybrik: a hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3383\u20133393 (2021)","key":"28_CR20","DOI":"10.1109\/CVPR46437.2021.00339"},{"doi-asserted-by":"crossref","unstructured":"Ling, L., et\u00a0al.: Dl3dv-10k: a large-scale scene dataset for deep learning-based 3d vision. arXiv preprint arXiv:2312.16256 (2023)","key":"28_CR21","DOI":"10.1109\/CVPR52733.2024.02092"},{"issue":"10","key":"28_CR22","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2020","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: Ntu rgb+d 120: a large-scale benchmark for 3d human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Liu, J., Rojas, J., Li, Y., Liang, Z., Guan, Y., Xi, N., Zhu, H.: A graph attention spatio-temporal convolutional network for 3d human pose estimation in video. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 3374\u20133380. IEEE (2021)","key":"28_CR23","DOI":"10.1109\/ICRA48506.2021.9561605"},{"doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. In: Seminal Graphics Papers: Pushing the Boundaries, vol. 2, pp. 851\u2013866 (2023)","key":"28_CR24","DOI":"10.1145\/3596711.3596800"},{"doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Transflow: transformer as flow learner. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18063\u201318073 (2023)","key":"28_CR25","DOI":"10.1109\/CVPR52729.2023.01732"},{"doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3d human pose in the wild using imus and a moving camera. In: European Conference on Computer Vision (ECCV), September 2018","key":"28_CR26","DOI":"10.1007\/978-3-030-01249-6_37"},{"doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","key":"28_CR27","DOI":"10.3115\/v1\/D14-1162"},{"issue":"8","key":"28_CR28","doi-asserted-by":"publisher","first-page":"4401","DOI":"10.1007\/s00521-023-09227-z","volume":"36","author":"K Radouane","year":"2024","unstructured":"Radouane, K., Tchechmedjiev, A., Lagarde, J., Ranwez, S.: Motion2language, unsupervised learning of synchronized semantic motion segmentation. Neural Comput. Appl. 36(8), 4401\u20134420 (2024)","journal-title":"Neural Comput. Appl."},{"doi-asserted-by":"crossref","unstructured":"Rong, Y., Shiratori, T., Joo, H.: Frankmocap: fast monocular 3d hand and body motion capture by regression and integration. arXiv preprint arXiv:2008.08324 (2020)","key":"28_CR29","DOI":"10.1109\/ICCVW54120.2021.00201"},{"doi-asserted-by":"crossref","unstructured":"Rong, Y., Shiratori, T., Joo, H.: Frankmocap: A monocular 3d whole-body pose estimation system via regression and integration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1749\u20131759 (2021)","key":"28_CR30","DOI":"10.1109\/ICCVW54120.2021.00201"},{"doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: Ntu rgb+d: a large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","key":"28_CR31","DOI":"10.1109\/CVPR.2016.115"},{"doi-asserted-by":"crossref","unstructured":"Shi, X., et al.: Videoflow: exploiting temporal cues for multi-frame optical flow estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12469\u201312480 (2023)","key":"28_CR32","DOI":"10.1109\/ICCV51070.2023.01146"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)","key":"28_CR33"},{"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)","key":"28_CR34","DOI":"10.1109\/CVPR.2018.00678"},{"doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","key":"28_CR35","DOI":"10.1109\/CVPR.2018.00931"},{"doi-asserted-by":"crossref","unstructured":"Tripathi, S., M\u00fcller, L., Huang, C.H.P., Taheri, O., Black, M.J., Tzionas, D.: 3d human pose estimation via intuitive physics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4713\u20134725 (2023)","key":"28_CR36","DOI":"10.1109\/CVPR52729.2023.00457"},{"doi-asserted-by":"publisher","unstructured":"Tripathi, S., Ranade, S., Tyagi, A., Agrawal, A.: Posenet3d: learning temporally consistent 3d human pose via knowledge distillation. In: 2020 International Conference on 3D Vision (3DV), pp. 311\u2013321 (2020). https:\/\/doi.org\/10.1109\/3DV50981.2020.00041","key":"28_CR37","DOI":"10.1109\/3DV50981.2020.00041"},{"unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Advances in neural information processing systems 30 (2017)","key":"28_CR38"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)","key":"28_CR39"},{"issue":"5","key":"28_CR40","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1109\/TIFS.2018.2878538","volume":"14","author":"T Wang","year":"2018","unstructured":"Wang, T., Qiao, M., Lin, Z., Li, C., Snoussi, H., Liu, Z., Choi, C.: Generative neural networks for anomaly detection in crowded scenes. IEEE Trans. Inf. Forensics Secur. 14(5), 1390\u20131399 (2018)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, Y., Xie, Z., Lu, G.: Deep unsupervised 3d sfm face reconstruction based on massive landmark bundle adjustment. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1350\u20131358 (2021)","key":"28_CR41","DOI":"10.1145\/3474085.3475689"},{"doi-asserted-by":"crossref","unstructured":"Wehrbein, T., Rudolph, M., Rosenhahn, B., Wandt, B.: Probabilistic monocular 3d human pose estimation with normalizing flows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11199\u201311208 (2021)","key":"28_CR42","DOI":"10.1109\/ICCV48922.2021.01101"},{"doi-asserted-by":"crossref","unstructured":"Xie, K., Wang, T., Iqbal, U., Guo, Y., Fidler, S., Shkurti, F.: Physics-based human motion estimation and synthesis from videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11532\u201311541 (2021)","key":"28_CR43","DOI":"10.1109\/ICCV48922.2021.01133"},{"doi-asserted-by":"crossref","unstructured":"Xu, J., Yu, Z., Ni, B., Yang, J., Yang, X., Zhang, W.: Deep kinematics analysis for monocular 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on computer vision and Pattern recognition, pp. 899\u2013908 (2020)","key":"28_CR44","DOI":"10.1109\/CVPR42600.2020.00098"},{"doi-asserted-by":"crossref","unstructured":"Yuan, Y., Iqbal, U., Molchanov, P., Kitani, K., Kautz, J.: Glamr: global occlusion-aware human mesh recovery with dynamic cameras. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11038\u201311049 (2022)","key":"28_CR45","DOI":"10.1109\/CVPR52688.2022.01076"},{"doi-asserted-by":"crossref","unstructured":"Zhu, W., Ma, X., Liu, Z., Liu, L., Wu, W., Wang, Y.: Motionbert: a unified perspective on learning human motion representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15085\u201315099 (2023)","key":"28_CR46","DOI":"10.1109\/ICCV51070.2023.01385"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2071-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T16:03:53Z","timestamp":1735747433000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2071-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620708","9789819620715"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2071-5_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","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":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}