{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:09:17Z","timestamp":1777500557689,"version":"3.51.4"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972187"],"award-info":[{"award-number":["61972187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2021J011005"],"award-info":[{"award-number":["2021J011005"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00530-024-01523-5","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T13:02:49Z","timestamp":1729774969000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DSTANet: learning a dual-stream model for anomaly driving action detection using spatio-temporal and appearance features"],"prefix":"10.1007","volume":"30","author":[{"given":"Zhonghua","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuoyong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,24]]},"reference":[{"issue":"6","key":"1523_CR1","doi-asserted-by":"publisher","first-page":"5122","DOI":"10.1109\/TITS.2023.3332350","volume":"25","author":"G Li","year":"2023","unstructured":"Li, G., Lin, Y., Ouyang, D., Li, S., Luo, X., Qu, X., Pi, D., Li, S.E.: A rgb-thermal image segmentation method based on parameter sharing and attention fusion for safe autonomous driving. IEEE Trans. Intell. Transp. Syst. 25(6), 5122\u20135137 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1523_CR2","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.jsr.2022.06.002","volume":"82","author":"H Ge","year":"2022","unstructured":"Ge, H., Bo, Y., Sun, H., Zheng, M., Lu, Y.: A review of research on driving distraction based on bibliometrics and co-occurrence: focus on driving distraction recognition methods. J. Saf. Res. 82, 261\u2013274 (2022)","journal-title":"J. Saf. Res."},{"issue":"2","key":"1523_CR3","first-page":"1594","volume":"24","author":"H Wang","year":"2022","unstructured":"Wang, H., Chen, J., Huang, Z., Li, B., Lv, J., Xi, J., Wu, B., Zhang, J., Wu, Z.: Fpt: fine-grained detection of driver distraction based on the feature pyramid vision transformer. IEEE Trans. Intell. Transp. Syst. 24(2), 1594\u20131608 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1523_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105309","volume":"115","author":"HV Koay","year":"2022","unstructured":"Koay, H.V., Chuah, J.H., Chow, C.-O., Chang, Y.-L.: Detecting and recognizing driver distraction through various data modality using machine learning: A review, recent advances, simplified framework and open challenges (2014\u20132021). Eng. Appl. Artif. Intell. 115, 105309 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1523_CR5","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.future.2022.02.007","volume":"132","author":"W Xiao","year":"2022","unstructured":"Xiao, W., Liu, H., Ma, Z., Chen, W.: Attention-based deep neural network for driver behavior recognition. Futur. Gener. Comput. Syst. 132, 152\u2013161 (2022)","journal-title":"Futur. Gener. Comput. Syst."},{"issue":"1","key":"1523_CR6","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s00530-022-00979-7","volume":"29","author":"W Liu","year":"2023","unstructured":"Liu, W., Cao, J., Zhu, Y., Liu, B., Zhu, X.: Real-time anomaly detection on surveillance video with two-stream spatio-temporal generative model. Multimedia Syst. 29(1), 59\u201371 (2023)","journal-title":"Multimedia Syst."},{"key":"1523_CR7","doi-asserted-by":"crossref","unstructured":"Martin, M., Voit, M., Stiefelhagen, R.: Dynamic interaction graphs for driver activity recognition. In: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp. 1\u20137 (2020). IEEE","DOI":"10.1109\/ITSC45102.2020.9294520"},{"key":"1523_CR8","doi-asserted-by":"crossref","unstructured":"Kopuklu, O., Zheng, J., Xu, H., Rigoll, G.: Driver anomaly detection: a dataset and contrastive learning approach. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 91\u2013100 (2021)","DOI":"10.1109\/WACV48630.2021.00014"},{"issue":"7","key":"1523_CR9","doi-asserted-by":"publisher","first-page":"1885","DOI":"10.1007\/s11760-022-02148-9","volume":"16","author":"X Hu","year":"2022","unstructured":"Hu, X., Lian, J., Zhang, D., Gao, X., Jiang, L., Chen, W.: Video anomaly detection based on 3d convolutional auto-encoder. SIViP 16(7), 1885\u20131893 (2022)","journal-title":"SIViP"},{"key":"1523_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119629","volume":"219","author":"I Jegham","year":"2023","unstructured":"Jegham, I., Alouani, I., Khalifa, A.B., Mahjoub, M.A.: Deep learning-based hard spatial attention for driver in-vehicle action monitoring. Expert Syst. Appl. 219, 119629 (2023)","journal-title":"Expert Syst. Appl."},{"key":"1523_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.115960","volume":"88","author":"I Jegham","year":"2020","unstructured":"Jegham, I., Khalifa, A.B., Alouani, I., Mahjoub, M.A.: A novel public dataset for multimodal multiview and multispectral driver distraction analysis: 3mdad. Signal Process. Image Commun. 88, 115960 (2020)","journal-title":"Signal Process. Image Commun."},{"key":"1523_CR12","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., Martin, S., Tawari, A., Trivedi, M.M.: Head, eye, and hand patterns for driver activity recognition. In: 2014 22nd International Conference on Pattern Recognition, pp. 660\u2013665 (2014). IEEE","DOI":"10.1109\/ICPR.2014.124"},{"key":"1523_CR13","doi-asserted-by":"crossref","unstructured":"Xu, L., Fujimura, K.: Real-time driver activity recognition with random forests. In: Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, pp. 1\u20138 (2014)","DOI":"10.1145\/2667317.2667333"},{"key":"1523_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2021.101280","volume":"48","author":"L Zhao","year":"2021","unstructured":"Zhao, L., Yang, F., Bu, L., Han, S., Zhang, G., Luo, Y.: Driver behavior detection via adaptive spatial attention mechanism. Adv. Eng. Inform. 48, 101280 (2021)","journal-title":"Adv. Eng. Inform."},{"key":"1523_CR15","doi-asserted-by":"publisher","first-page":"8464","DOI":"10.1109\/TMM.2022.3197364","volume":"26","author":"H Liu","year":"2022","unstructured":"Liu, H., Liu, T., Chen, Y., Zhang, Z., Li, Y.-F.: Ehpe: skeleton cues-based gaussian coordinate encoding for efficient human pose estimation. IEEE Trans. Multimedia 26, 8464\u20138475 (2022)","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"1523_CR16","doi-asserted-by":"publisher","first-page":"8068","DOI":"10.1109\/TII.2023.3266366","volume":"20","author":"T Liu","year":"2022","unstructured":"Liu, T., Liu, H., Yang, B., Zhang, Z.: Ldcnet: limb direction cues-aware network for flexible human pose estimation in industrial behavioral biometrics systems. IEEE Trans. Indust. Inform. 20(6), 8068\u20138078 (2023)","journal-title":"IEEE Trans. Indust. Inform."},{"key":"1523_CR17","doi-asserted-by":"publisher","first-page":"104207","DOI":"10.1109\/ACCESS.2020.2999633","volume":"8","author":"M Liu","year":"2020","unstructured":"Liu, M., Li, Y., Liu, H.: 3d gaze estimation for head-mounted eye tracking system with auto-calibration method. IEEE Access 8, 104207\u2013104215 (2020)","journal-title":"IEEE Access"},{"key":"1523_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3118090","volume":"70","author":"M Liu","year":"2021","unstructured":"Liu, M., Li, Y., Liu, H.: Robust 3-d gaze estimation via data optimization and saliency aggregation for mobile eye-tracking systems. IEEE Trans. Instrum. Meas. 70, 1\u201310 (2021)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"10","key":"1523_CR19","doi-asserted-by":"publisher","first-page":"7107","DOI":"10.1109\/TII.2022.3143605","volume":"18","author":"H Liu","year":"2022","unstructured":"Liu, H., Liu, T., Zhang, Z., Sangaiah, A.K., Yang, B., Li, Y.: Arhpe: asymmetric relation-aware representation learning for head pose estimation in industrial human-computer interaction. IEEE Trans. Ind. Inf. 18(10), 7107\u20137117 (2022)","journal-title":"IEEE Trans. Ind. Inf."},{"key":"1523_CR20","doi-asserted-by":"publisher","first-page":"6289","DOI":"10.1109\/TIP.2023.3331309","volume":"32","author":"H Liu","year":"2023","unstructured":"Liu, H., Zhang, C., Deng, Y., Liu, T., Zhang, Z., Li, Y.-F.: Orientation cues-aware facial relationship representation for head pose estimation via transformer. IEEE Trans. Image Process. 32, 6289\u20136302 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"1523_CR21","doi-asserted-by":"crossref","unstructured":"Rangesh, A., Trivedi, M.: Forced spatial attention for driver foot activity classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00308"},{"issue":"2","key":"1523_CR22","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1109\/TCSS.2022.3158480","volume":"10","author":"L Su","year":"2022","unstructured":"Su, L., Sun, C., Cao, D., Khajepour, A.: Efficient driver anomaly detection via conditional temporal proposal and classification network. IEEE Trans. Comput. Soc. Syst. 10(2), 736\u2013745 (2022)","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"1523_CR23","doi-asserted-by":"crossref","unstructured":"Yang, Y., Fu, Z., Naqvi, S.M.: A two-stream information fusion approach to abnormal event detection in video. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5787\u20135791 (2022). IEEE","DOI":"10.1109\/ICASSP43922.2022.9746420"},{"key":"1523_CR24","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.inffus.2022.08.009","volume":"89","author":"P Ping","year":"2023","unstructured":"Ping, P., Huang, C., Ding, W., Liu, Y., Chiyomi, M., Kazuya, T.: Distracted driving detection based on the fusion of deep learning and causal reasoning. Inform. Fusion 89, 121\u2013142 (2023)","journal-title":"Inform. Fusion"},{"key":"1523_CR25","first-page":"1","volume":"99","author":"Z Guo","year":"2024","unstructured":"Guo, Z., Liu, Q., Zhang, L., Li, Z., Li, G.: L-tla: a lightweight driver distraction detection method based on three-level attention mechanisms. IEEE Trans. Reliab. 99, 1\u201312 (2024)","journal-title":"IEEE Trans. Reliab."},{"issue":"2","key":"1523_CR26","doi-asserted-by":"publisher","first-page":"3168","DOI":"10.1109\/TIV.2024.3353253","volume":"9","author":"Y Ma","year":"2024","unstructured":"Ma, Y., Du, R., Abdelraouf, A., Han, K., Gupta, R., Wang, Z.: Driver digital twin for online recognition of distracted driving behaviors. IEEE Trans. Intell. Veh. 9(2), 3168\u20133180 (2024)","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"9","key":"1523_CR27","doi-asserted-by":"publisher","first-page":"11602","DOI":"10.1109\/TITS.2024.3381175","volume":"25","author":"MZ Hasan","year":"2024","unstructured":"Hasan, M.Z., Chen, J., Wang, J., Rahman, M.S., Joshi, A., Velipasalar, S., Hegde, C., Sharma, A., Sarkar, S.: Vision-language models can identify distracted driver behavior from naturalistic videos. IEEE Trans. Intell. Transp. Syst. 25(9), 11602\u201311616 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1523_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2023.110136","volume":"169","author":"Z Li","year":"2024","unstructured":"Li, Z., Su, H., Li, B., Luan, H., Gu, M., Fang, X.: Event-based diffractive neural network chip for dynamic action recognition. Opt. Laser Technol. 169, 110136 (2024)","journal-title":"Opt. Laser Technol."},{"issue":"4","key":"1523_CR29","doi-asserted-by":"publisher","first-page":"041119","DOI":"10.1117\/1.JEI.22.4.041119","volume":"22","author":"E Ohn-Bar","year":"2013","unstructured":"Ohn-Bar, E., Martin, S., Trivedi, M.M.: Driver hand activity analysis in naturalistic driving studies: challenges, algorithms, and experimental studies. J. Electron. Imaging 22(4), 041119\u2013041119 (2013)","journal-title":"J. Electron. Imaging"},{"key":"1523_CR30","doi-asserted-by":"crossref","unstructured":"Das, N., Ohn-Bar, E., Trivedi, M.M.: On performance evaluation of driver hand detection algorithms: Challenges, dataset, and metrics. In: 2015 IEEE 18th International Conference on Intelligent Transportation Systems, pp. 2953\u20132958 (2015). IEEE","DOI":"10.1109\/ITSC.2015.473"},{"key":"1523_CR31","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc, O., Ledwon, T., Rong, Y., Kose, N., Rigoll, G.: Drivermhg: A multi-modal dataset for dynamic recognition of driver micro hand gestures and a real-time recognition framework. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 77\u201384 (2020). IEEE","DOI":"10.1109\/FG47880.2020.00041"},{"key":"1523_CR32","unstructured":"Abouelnaga, Y., Eraqi, H.M., Moustafa, M.N.: Real-time distracted driver posture classification. arXiv preprint arXiv:1706.09498 (2017)"},{"key":"1523_CR33","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":"1523_CR34","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"},{"key":"1523_CR35","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":"1523_CR36","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":"1523_CR37","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J.W., Carneiro, G.: Weaklysupervised 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":"1523_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109348","volume":"252","author":"Q Li","year":"2022","unstructured":"Li, Q., Yang, R., Xiao, F., Bhanu, B., Zhang, F.: Attention-based anomaly detection in multi-view surveillance videos. Knowl.-Based Syst. 252, 109348 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"1523_CR39","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. 37, pp. 387\u2013395 (2023)","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"1523_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, M., Wang, J., Qi, Q., Sun, H., Zhuang, Z., Ren, P., Ma, R., Liao, J.: Multi-scale video anomaly detection by multi-grained spatio-temporal representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17385\u201317394 (2024)","DOI":"10.1109\/CVPR52733.2024.01646"},{"key":"1523_CR41","doi-asserted-by":"crossref","unstructured":"Wu, P., Zhou, X., Pang, G., Sun, Y., Liu, J., Wang, P., Zhang, Y.: Open-vocabulary video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18297\u201318307 (2024)","DOI":"10.1109\/CVPR52733.2024.01732"},{"key":"1523_CR42","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.1109\/TIP.2024.3374070","volume":"33","author":"P Wu","year":"2024","unstructured":"Wu, P., Liu, J., He, X., Peng, Y., Wang, P., Zhang, Y.: Toward video anomaly retrieval from video anomaly detection: New benchmarks and model. IEEE Trans. Image Process. 33, 2213\u20132225 (2024)","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"1523_CR43","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.1109\/TPAMI.2023.3311447","volume":"45","author":"J Gao","year":"2023","unstructured":"Gao, J., Chen, M., Xu, C.: Vectorized evidential learning for weakly-supervised temporal action localization. IEEE Trans Pattern Anal. Mach. Intell. 45(12), 15949\u201315963 (2023)","journal-title":"IEEE Trans Pattern Anal. Mach. Intell."},{"key":"1523_CR44","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: I know the relationships: Zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8303\u20138311 (2019)","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"1523_CR45","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.future.2021.10.033","volume":"129","author":"W Ullah","year":"2022","unstructured":"Ullah, W., Ullah, A., Hussain, T., Muhammad, K., Heidari, A.A., Del Ser, J., Baik, S.W., De Albuquerque, V.H.C.: Artificial intelligence of things-assisted two-stream neural network for anomaly detection in surveillance big video data. Futur. Gener. Comput. Syst. 129, 286\u2013297 (2022)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"1523_CR46","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1016\/j.ins.2022.05.092","volume":"606","author":"T Liu","year":"2022","unstructured":"Liu, T., Ma, Y., Yang, W., Ji, W., Wang, R., Jiang, P.: Spatial-temporal interaction learning based two-stream network for action recognition. Inf. Sci. 606, 864\u2013876 (2022)","journal-title":"Inf. Sci."},{"key":"1523_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, Y., Wang, H.: Two-stream networks for weakly-supervised temporal action localization with semantic-aware mechanisms. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18878\u201318887 (2023)","DOI":"10.1109\/CVPR52729.2023.01810"},{"key":"1523_CR48","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1523_CR49","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1523_CR50","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607 (2020). PMLR"},{"key":"1523_CR51","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"issue":"8","key":"1523_CR52","doi-asserted-by":"publisher","first-page":"13242","DOI":"10.1109\/TITS.2021.3123127","volume":"23","author":"M Tan","year":"2021","unstructured":"Tan, M., Ni, G., Liu, X., Zhang, S., Wu, X., Wang, Y., Zeng, R.: Bidirectional posture-appearance interaction network for driver behavior recognition. IEEE Trans. Intell. Transp. Syst. 23(8), 13242\u201313254 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1523_CR53","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A., Morency, L.-P.: Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"1523_CR54","doi-asserted-by":"crossref","unstructured":"Cai, R., Zhang, H., Liu, W., Gao, S., Hao, Z.: Appearance-motion memory consistency network for video anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 938\u2013946 (2021)","DOI":"10.1609\/aaai.v35i2.16177"},{"key":"1523_CR55","doi-asserted-by":"crossref","unstructured":"Thakare, K.V., Raghuwanshi, Y., Dogra, D.P., Choi, H., Kim, I.-J.: Dyannet: A scene dynamicity guided self-trained video anomaly detection network. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5541\u20135550 (2023)","DOI":"10.1109\/WACV56688.2023.00550"},{"key":"1523_CR56","doi-asserted-by":"crossref","unstructured":"Li, Y., Yu, A.W., Meng, T., Caine, B., Ngiam, J., Peng, D., Shen, J., Lu, Y., Zhou, D., Le, Q.V., et al.: Deepfusion: Lidar-camera deep fusion for multi-modal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17182\u201317191 (2022)","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"1523_CR57","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 297\u2013304 (2010). JMLR Workshop and Conference Proceedings"},{"key":"1523_CR58","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., Krishnan, D.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1523_CR59","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Safdari, R., Lotfi, D., Sarfraz, S., Stiefelhagen, R., Van\u00a0Gool, L.: Vi2clr: Video and image for visual contrastive learning of representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1502\u20131512 (2021)","DOI":"10.1109\/ICCV48922.2021.00153"},{"key":"1523_CR60","doi-asserted-by":"crossref","unstructured":"Khan, S.S., Shen, Z., Sun, H., Patel, A., Abedi, A.: Supervised contrastive learning for detecting anomalous driving behaviours from multimodal videos. In: 2022 19th Conference on Robots and Vision (CRV), pp. 16\u201323 (2022). IEEE","DOI":"10.1109\/CRV55824.2022.00011"},{"issue":"6","key":"1523_CR61","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1002\/pip.3518","volume":"30","author":"L Bommes","year":"2022","unstructured":"Bommes, L., Hoffmann, M., Buerhop-Lutz, C., Pickel, T., Hauch, J., Brabec, C., Maier, A., Marius Peters, I.: Anomaly detection in ir images of pv modules using supervised contrastive learning. Prog. Photovolt. Res. Appl. 30(6), 597\u2013614 (2022)","journal-title":"Prog. Photovolt. Res. Appl."},{"issue":"8","key":"1523_CR62","doi-asserted-by":"publisher","first-page":"4257","DOI":"10.1109\/TCSVT.2023.3243725","volume":"33","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Xie, Y., Ding, W., Wang, Z.: Cross on cross attention: Deep fusion transformer for image captioning. IEEE Trans. Circuits Syst. Video Technol. 33(8), 4257\u20134268 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1523_CR63","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118631","volume":"211","author":"C Guo","year":"2023","unstructured":"Guo, C., Fan, D., Jiang, Z., Zhang, D.: Mdfn: mask deep fusion network for visible and infrared image fusion without reference ground-truth. Expert Syst. Appl. 211, 118631 (2023)","journal-title":"Expert Syst. Appl."},{"key":"1523_CR64","unstructured":"Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S.A., Binder, A., M\u00fcller, E., Kloft, M.: Deep one-class classification. In: International Conference on Machine Learning, pp. 4393\u20134402 (2018). PMLR"},{"key":"1523_CR65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108080","volume":"119","author":"H Cevikalp","year":"2021","unstructured":"Cevikalp, H., Uzun, B., K\u00f6p\u00fckl\u00fc, O., Ozturk, G.: Deep compact polyhedral conic classifier for open and closed set recognition. Pattern Recogn. 119, 108080 (2021)","journal-title":"Pattern Recogn."},{"issue":"2","key":"1523_CR66","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TPAMI.2019.2934455","volume":"43","author":"H Cevikalp","year":"2019","unstructured":"Cevikalp, H., Saglamlar, H.: Polyhedral conic classifiers for computer vision applications and open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 608\u2013622 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1523_CR67","doi-asserted-by":"crossref","unstructured":"Anagnostou, P., Mitianoudis, N.: A lightweight convgru network for distracted driving detection. In: 2023 24th International Conference on Digital Signal Processing (DSP), pp. 1\u20135 (2023). IEEE","DOI":"10.1109\/DSP58604.2023.10167971"},{"key":"1523_CR68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109385","volume":"138","author":"H Cevikalp","year":"2023","unstructured":"Cevikalp, H., Uzun, B., Salk, Y., Saribas, H., K\u00f6p\u00fckl\u00fc, O.: From anomaly detection to open set recognition: Bridging the gap. Pattern Recogn. 138, 109385 (2023)","journal-title":"Pattern Recogn."},{"key":"1523_CR69","doi-asserted-by":"crossref","unstructured":"Ma, Y., Upadhyay, D., Sanchez, V., Atote, B., Nikan, S., Guha, T.: Robust multiview multimodal driver monitoring system using masked multi-head self-attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132624 (2023)","DOI":"10.1109\/CVPRW59228.2023.00260"},{"key":"1523_CR70","doi-asserted-by":"crossref","unstructured":"Koay, H.V., Chuah, J.H., Chow, C.-O.: Contrastive learning with video transformer for driver distraction detection through multiview and multimodal video. In: 2023 IEEE Region 10 Symposium (TENSYMP), pp. 1\u20136 (2023). IEEE","DOI":"10.1109\/TENSYMP55890.2023.10223643"},{"key":"1523_CR71","doi-asserted-by":"crossref","unstructured":"Yu, Z., Qin, Y., Li, X., Wang, Z., Zhao, C., Lei, Z., Zhao, G.: Multi-modal face anti-spoofing based on central difference networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 650\u2013651 (2020)","DOI":"10.1109\/CVPRW50498.2020.00333"},{"issue":"11","key":"1523_CR72","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01523-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01523-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01523-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T04:08:50Z","timestamp":1734322130000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01523-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,24]]},"references-count":72,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1523"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01523-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4321265\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,24]]},"assertion":[{"value":"25 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Written informed consent for publication of this paper was obtained from the Fujian University of Technology and all authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"325"}}