{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T13:44:03Z","timestamp":1745588643787,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819759330"},{"type":"electronic","value":"9789819759347"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5934-7_6","type":"book-chapter","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T08:02:36Z","timestamp":1723449756000},"page":"59-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Omni-TransPose: Fusion of OmniPose and Transformer Architecture for Improving Action Detection"],"prefix":"10.1007","author":[{"given":"Khac-Anh","family":"Phu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7554-1707","authenticated-orcid":false,"given":"Van-Dung","family":"Hoang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Van-Tuong-Lan","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quang-Khai","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,13]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Thi, T.H., Zhang, J., Cheng, L., Wang, L., Satoh, S.: Human action recognition and localization in video using structured learning of local space-time features. In: Paper presented at the 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance (2010)","key":"6_CR1","DOI":"10.1109\/AVSS.2010.76"},{"issue":"4","key":"6_CR2","doi-asserted-by":"publisher","first-page":"3357","DOI":"10.3233\/JIFS-181085","volume":"36","author":"V-H Pham","year":"2019","unstructured":"Pham, V.-H., Jo, K.-H., Hoang, V.-D.: Scalable local features and hybrid classifiers for improving action recognition. J. Intell. Fuzzy Syst. 36(4), 3357\u20133372 (2019)","journal-title":"J. Intell. Fuzzy Syst."},{"issue":"3","key":"6_CR3","doi-asserted-by":"publisher","first-page":"3200","DOI":"10.1109\/TPAMI.2022.3183112","volume":"45","author":"Z Sun","year":"2023","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human action recognition from various data modalities: a review. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3200\u20133225 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3183112","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"6_CR4","doi-asserted-by":"publisher","first-page":"201","DOI":"10.3758\/BF03212378","volume":"14","author":"G Johansson","year":"1973","unstructured":"Johansson, G.: Visual perception of biological motion and a model for its analysis. Percept. Psychophys. 14(2), 201\u2013211 (1973). https:\/\/doi.org\/10.3758\/BF03212378","journal-title":"Percept. Psychophys."},{"doi-asserted-by":"crossref","unstructured":"Datir, A.P., Funde, S.S., Bhore, N.T., Gawande, S.B., Dhade, P., Nehete, P.: A Comprehensive survey on Real Time human pose estimation. Paper presented at the 2023 IEEE International Students\u2019 Conference on Electrical, Electronics and Computer Science (SCEECS), 18\u201319 February 2023 (2023)","key":"6_CR5","DOI":"10.1109\/SCEECS57921.2023.10063000"},{"doi-asserted-by":"publisher","unstructured":"Vaswani, A.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30 (2017). https:\/\/doi.org\/10.48550\/arXiv.1706.03762","key":"6_CR6","DOI":"10.48550\/arXiv.1706.03762"},{"doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations, 3 June 2021. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","key":"6_CR7","DOI":"10.48550\/arXiv.2010.11929"},{"doi-asserted-by":"publisher","unstructured":"Mazzia, V., Angarano, S., Salvetti, F., Angelini, F., Chiaberge, M.: Action transformer: a self-attention model for short-time pose-based human action recognition. In: Computer Vision and Pattern Recognition, vol. 124, April 2022. https:\/\/doi.org\/10.1016\/j.patcog.2021.108487","key":"6_CR8","DOI":"10.1016\/j.patcog.2021.108487"},{"doi-asserted-by":"publisher","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 10347\u201310357, July 2021. https:\/\/doi.org\/10.48550\/arXiv.2012.12877","key":"6_CR9","DOI":"10.48550\/arXiv.2012.12877"},{"doi-asserted-by":"publisher","unstructured":"D\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., Sagun, L.: ConViT: improving vision transformers with soft convolutional inductive biases. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 2286\u20132296, 24 July 2021. https:\/\/doi.org\/10.1088\/1742-5468\/ac9830","key":"6_CR10","DOI":"10.1088\/1742-5468\/ac9830"},{"doi-asserted-by":"publisher","unstructured":"Yang, F., Yang, H., Fu, J., Lu, H., Guo, B.: Learning texture transformer network for image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5791\u20135800, June 2020. https:\/\/doi.org\/10.48550\/arXiv.2006.04139","key":"6_CR11","DOI":"10.48550\/arXiv.2006.04139"},{"doi-asserted-by":"publisher","unstructured":"Hongyu Zhu, H., Liu, H., Zhu, C., Deng, Z., Sun, X.: Learning spatial-temporal deformable networks for unconstrained face alignment and tracking in videos. Pattern Recogn. 107, 107354 (2020). https:\/\/doi.org\/10.1016\/j.patcog.2020.107354. ISSN 0031-3203","key":"6_CR12","DOI":"10.1016\/j.patcog.2020.107354"},{"doi-asserted-by":"publisher","unstructured":"Artacho, B., Savakis, A.: OmniPose: a multi-scale framework for multi-person pose estimation. ArXiv 2021. https:\/\/doi.org\/10.48550\/arXiv.2103.10180","key":"6_CR13","DOI":"10.48550\/arXiv.2103.10180"},{"unstructured":"Cimen, G., Maurhofer, C., Sumner, R.W., Guay, M.: AR poser: automatically augmenting mobile pictures with digital avatars imitating poses. In: 12th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing 2018, July 2018","key":"6_CR14"},{"doi-asserted-by":"publisher","unstructured":"Cormier, M., Clepe, A., Specker, A., Beyerer, J.: Where are we with Human Pose Estimation in Real-World Surveillance? In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Waikoloa, HI, USA, pp. 591\u2013601 (2022). https:\/\/doi.org\/10.1109\/WACVW54805.2022.00065","key":"6_CR15","DOI":"10.1109\/WACVW54805.2022.00065"},{"doi-asserted-by":"publisher","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29","key":"6_CR16","DOI":"10.1007\/978-3-319-46484-8_29"},{"unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems, pp. 1799\u20131807 (2014)","key":"6_CR17"},{"doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","key":"6_CR18","DOI":"10.1109\/CVPR.2015.7298965"},{"doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep High-Resolution Representation Learning for Human Pose Estimation (2019). arXiv:1902.09212","key":"6_CR19","DOI":"10.1109\/CVPR.2019.00584"},{"doi-asserted-by":"publisher","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3","key":"6_CR20","DOI":"10.1007\/978-3-319-46466-4_3"},{"doi-asserted-by":"crossref","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: ICCV, pp. 1290\u20131299 (2017)","key":"6_CR21","DOI":"10.1109\/ICCV.2017.144"},{"doi-asserted-by":"publisher","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29","key":"6_CR22","DOI":"10.1007\/978-3-030-01231-1_29"},{"doi-asserted-by":"publisher","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","key":"6_CR23","DOI":"10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P.V., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR, pp. 3686\u20133693 (2014)","key":"6_CR24","DOI":"10.1109\/CVPR.2014.471"},{"doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: CVPR, pp. 5167\u20135176 (2018)","key":"6_CR25","DOI":"10.1109\/CVPR.2018.00542"},{"doi-asserted-by":"publisher","unstructured":"Artacho, B., Savakis, A.: UniPose: unified human pose estimation in single images and videos. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 7033\u20137042 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00706","key":"6_CR26","DOI":"10.1109\/CVPR42600.2020.00706"}],"container-title":["Communications in Computer and Information Science","Recent Challenges in Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5934-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T06:03:46Z","timestamp":1733119426000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5934-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819759330","9789819759347"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5934-7_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"13 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ras Al Khaimah","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Arab Emirates","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2024\/index.php#about","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}