{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T21:16:11Z","timestamp":1779311771727,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s00138-024-01550-2","type":"journal-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T07:02:21Z","timestamp":1715583741000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Thermal infrared action recognition with two-stream shift Graph Convolutional Network"],"prefix":"10.1007","volume":"35","author":[{"given":"Jishi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junnian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dalin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiongfeng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"issue":"6","key":"1550_CR1","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/s00138-023-01475-2","volume":"34","author":"MA Raza","year":"2023","unstructured":"Raza, M.A., Fisher, R.B.: Vision-based approach to assess performance levels while eating. Mach. Vis. Appl. 34(6), 124 (2023)","journal-title":"Mach. Vis. Appl."},{"key":"1550_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3587931","volume":"55","author":"H Gammulle","year":"2022","unstructured":"Gammulle, H., Ahmedt-Aristizabal, D., Denman, S., Tychsen-Smith, L., Petersson, L., Fookes, C.: Continuous human action recognition for human\u2013machine interaction: a review. ACM Comput. Surv. 55, 1\u201338 (2022)","journal-title":"ACM Comput. Surv."},{"key":"1550_CR3","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2016.05.094","volume":"212","author":"C Gao","year":"2016","unstructured":"Gao, C., Du, Y., Liu, J., Lv, J., Yang, L., Meng, D., Hauptmann, A.: Infar dataset: infrared action recognition at different times. Neurocomputing 212, 36\u201347 (2016)","journal-title":"Neurocomputing"},{"key":"1550_CR4","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Rozgic, V., Adali, S.: Learning spatiotemporal features for infrared action recognition with 3d convolutional neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 309\u2013317 (2017)","DOI":"10.1109\/CVPRW.2017.44"},{"key":"1550_CR5","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1109\/LSP.2018.2823910","volume":"25","author":"Y Liu","year":"2018","unstructured":"Liu, Y., Lu, Z., Li, J., Yang, T., Yao, C.: Global temporal representation based cnns for infrared action recognition. IEEE Signal Process. Lett. 25, 848\u2013852 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"1550_CR6","doi-asserted-by":"crossref","unstructured":"Wang, L., Gao, C., Zhao, Y., Song, T., Feng, Q.: Infrared and visible image registration using transformer adversarial network. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1248\u20131252 (2018)","DOI":"10.1109\/ICIP.2018.8451370"},{"key":"1550_CR7","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/TMM.2021.3050069","volume":"24","author":"X Chen","year":"2021","unstructured":"Chen, X., Gao, C., Li, C., Yang, Y., Meng, D.: Infrared action detection in the dark via cross-stream attention mechanism. IEEE Trans. Multimed. 24, 288\u2013300 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"1550_CR8","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464\u20137475 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1550_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H., Xie, S., Tai, Y.-W., Lu, C.: Rmpe: regional multi-person pose estimation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2353\u20132362 (2016)","DOI":"10.1109\/ICCV.2017.256"},{"key":"1550_CR10","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. ArXiv, pp. 7444\u20137452 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1550_CR11","doi-asserted-by":"publisher","first-page":"10535","DOI":"10.1109\/TPAMI.2023.3261282","volume":"45","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Demiris, Y.: Visible and infrared image fusion using deep learning. IEEE Trans. Pattern Anal. Mach. Intell. 45, 10535\u201310554 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1550_CR12","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.neucom.2022.12.042","volume":"523","author":"T Si","year":"2023","unstructured":"Si, T., He, F., Li, P., Gao, X.: Tri-modality consistency optimization with heterogeneous augmented images for visible-infrared person re-identification. Neurocomputing 523, 170\u2013181 (2023)","journal-title":"Neurocomputing"},{"key":"1550_CR13","doi-asserted-by":"crossref","unstructured":"Liu, D., Yang, H., Shao, Y.: Fusion of infrared and visible light images for object detection based on CNN. In: 2021 10th International Conference on Internet Computing for Science and Engineering, pp. 110\u2013115 (2021)","DOI":"10.1145\/3485314.3485327"},{"key":"1550_CR14","doi-asserted-by":"crossref","unstructured":"Guo, H., Tang, T., Luo, G., Chen, R., Lu, Y., Wen, L.: Multi-domain pose network for multi-person pose estimation and tracking. ArXiv, pp. 209\u2013216 (2018)","DOI":"10.1007\/978-3-030-11012-3_17"},{"key":"1550_CR15","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1109\/JPROC.2010.2050290","volume":"98","author":"A Torralba","year":"2010","unstructured":"Torralba, A., Russell, B.C., Yuen, J.: Labelme: online image annotation and applications. Proc. IEEE 98, 1467\u20131484 (2010)","journal-title":"Proc. IEEE"},{"key":"1550_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3578495.3578502","volume":"13","author":"D Stefanics","year":"2021","unstructured":"Stefanics, D., Fox, M.: Coco annotator. ACM SIGMultimed. Rec. 13, 1\u20131 (2021)","journal-title":"ACM SIGMultimed. Rec."},{"key":"1550_CR17","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., He, X., Chen, W., Cheng, J., Lu, H.: Skeleton-based action recognition with shift graph convolutional network. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 180\u2013189 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"1550_CR18","doi-asserted-by":"crossref","unstructured":"Ramasinghe, S., Rodrigo, R.: Action recognition by single stream convolutional neural networks: an approach using combined motion and static information. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 101\u2013105 (2015)","DOI":"10.1109\/ACPR.2015.7486474"},{"key":"1550_CR19","doi-asserted-by":"crossref","unstructured":"Jain, M., J\u00e9gou, H., Bouthemy, P.: Better exploiting motion for better action recognition. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2555\u20132562 (2013)","DOI":"10.1109\/CVPR.2013.330"},{"key":"1550_CR20","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: Imagebert: cross-modal pre-training with large-scale weak-supervised image-text data. arXiv:2001.07966 (2020)"},{"key":"1550_CR21","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"6","key":"1550_CR22","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/s00138-023-01478-z","volume":"34","author":"K Ji","year":"2023","unstructured":"Ji, K., Lei, W., Zhang, W.: A deep retinex network for underwater low-light image enhancement. Mach. Vis. Appl. 34(6), 122 (2023)","journal-title":"Mach. Vis. Appl."},{"key":"1550_CR23","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"1550_CR24","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625\u20132634 (2014)","DOI":"10.21236\/ADA623249"},{"key":"1550_CR25","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497 (2014)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1550_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Sun, X., Zha, Z., Zeng, W.: Mict: mixed 3d\/2d convolutional tube for human action recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 449\u2013458 (2018)","DOI":"10.1109\/CVPR.2018.00054"},{"key":"1550_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"1550_CR28","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. arXiv:1406.2199 (2014)"},{"key":"1550_CR29","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Gool, L.: Temporal segment networks: towards good practices for deep action recognition. ArXiv, pp. 20\u201336 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"1550_CR30","unstructured":"Zhu, Y., Lan, Z., Newsam, S., Hauptmann, A.: Hidden two-stream convolutional networks for action recognition. arXiv:1704.00389 (2017)"},{"key":"1550_CR31","doi-asserted-by":"crossref","unstructured":"Liu, K., Liu, W., Gan, C., Tan, M., Ma, H.: T-c3d: temporal convolutional 3d network for real-time action recognition. ArXiv, pp. 7138\u20137145 (2018)","DOI":"10.1609\/aaai.v32i1.12333"},{"key":"1550_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zeng, H., Guo, S., Zhang, L.: Efficient long-range attention network for image super-resolution. ArXiv, pp. 649\u2013667 (2022)","DOI":"10.1007\/978-3-031-19790-1_39"},{"key":"1550_CR33","unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946 (2019)"},{"key":"1550_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zhu, Y., Wang, H., Chen, Y., Wu, G., Wang, L.: Extracting motion and appearance via inter-frame attention for efficient video frame interpolation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5682\u20135692 (2023)","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"1550_CR35","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.1007\/s11760-014-0677-9","volume":"9","author":"D-M Tsai","year":"2015","unstructured":"Tsai, D.-M., Chiu, W.-Y., Lee, M.-H.: Optical flow-motion history image (OF-MHI) for action recognition. Signal Image Video Process. 9, 1897\u20131906 (2015)","journal-title":"Signal Image Video Process."},{"key":"1550_CR36","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T.L., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., Murphy, K.: Towards accurate multi-person pose estimation in the wild. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3711\u20133719 (2017)","DOI":"10.1109\/CVPR.2017.395"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01550-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01550-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01550-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T19:09:25Z","timestamp":1722452965000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01550-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1550"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01550-2","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"11 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no conflict of interest in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"65"}}