{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T08:17:39Z","timestamp":1792225059507,"version":"4.4.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000},"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":["Vis Comput"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s00371-023-02936-5","type":"journal-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T02:01:38Z","timestamp":1688349698000},"page":"2555-2569","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["ConvFormer: parameter reduction in transformer models for 3D human pose estimation by leveraging dynamic multi-headed convolutional attention"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9725-4565","authenticated-orcid":false,"given":"Alec","family":"Diaz-Arias","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitriy","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,3]]},"reference":[{"key":"2936_CR1","doi-asserted-by":"crossref","unstructured":"Banik, S., Garc\u00cda, A.M., Knoll, A.: 3D human pose regression using graph convolutional network. In: 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA, pp. 924\u2013928 (2021)","DOI":"10.1109\/ICIP42928.2021.9506736"},{"key":"2936_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T.-J., Yuan, J., Thalmann, N.M.: Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2272\u20132281 (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"2936_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillob, A., Zagoruyko, S.: Ene-to-End Object Detection with Transformers. arXiv:2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2936_CR4","unstructured":"Chaitanya, K., Joshua, M., Hang, D., Roderick, M-S.: CpT: Convolutional Point Transformer for 3D Point Cloud Processing. arXiv:2111.10866 (2021)"},{"key":"2936_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Fang, C., Shen, X., Zhu, Y., Chen, Z., Luo, J.: Anatomy-aware 3d human pose estimation with bone-based pose decomposition. In: IEEE Transactions on Circuits and Systems for Video Technology (2021)","DOI":"10.1109\/TCSVT.2021.3057267"},{"key":"2936_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, X., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"2936_CR7","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mundhaada, A., Kusupati, U., Afaque, S., Sharma, A., Jain, A.: Learning 3D human pose from structure and motion. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"2936_CR8","doi-asserted-by":"crossref","unstructured":"Diaz-Arias, A., Messmore, M., Shin, D., Baek, S.: On the role of depth predictions for 3D human pose estimation. arXiv:2103.02521 (2021)","DOI":"10.2139\/ssrn.4067035"},{"key":"2936_CR9","doi-asserted-by":"crossref","unstructured":"Faang, H.S., Xu, Y., Wang, W., Liu, X., Zhu, S.C.: Learning pose grammar to encode human body configuration for 3d pose estimation. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12270"},{"key":"2936_CR10","doi-asserted-by":"crossref","unstructured":"He, Y., Yan, R., Fragkiadaki, K., Yu, S.: Epipolr transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7776\u20137785 (2020)","DOI":"10.1109\/CVPR42600.2020.00780"},{"issue":"7","key":"2936_CR11","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olarue, 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 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2936_CR12","unstructured":"Junfa, L., Juan, R., Yihui, L., Zhijun, L., Yisheng, G., Ning, X., Haifei, Z.: A graph attention spatio-temporal convolutional network for 3D human pose estimation in video. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi\u2019an, China, pp. 3374\u20133380 (2021)"},{"key":"2936_CR13","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"2936_CR14","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: Proceedings of International Conference on Learning Representations (ICLR) (2020)"},{"key":"2936_CR15","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagozz, S., Akbas, E.: Self-supervised learning of 3d human pose using multi-view geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1077\u20131086 (2019)","DOI":"10.1109\/CVPR.2019.00117"},{"key":"2936_CR16","unstructured":"Kolesnikov, A., Dosovitskiy, A., Weissenborn, D., Heigold, G., Uszkoreit, J., Beyer, L., Minderer, M., Dehghani, M., Houlsby, N., Gelly, S., Unterthiner, T., Zhai, X.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2021)"},{"key":"2936_CR17","doi-asserted-by":"crossref","unstructured":"Li, W., Hong, T., Hao, W., Picho, V., Van Gool, L.: MHFormer: multi-hypothesis transformer for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"2936_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Ke, L., Pratama, K., Tai, Y.W., Tang, C.K., Cheng, K.T.: Cascaded deep monocular 3D human pose estimation with evolutionary training data. arXiv:2006.07778 (2020)","DOI":"10.1109\/CVPR42600.2020.00621"},{"key":"2936_CR19","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Ding, R., Liu, M., Wang, P., Yang, W.: Exploiting temporal contexts with strided transformer for 3d human pose estimation. In: IEEE Transaactions on Multimedia (2022)","DOI":"10.1109\/TMM.2022.3141231"},{"key":"2936_CR20","unstructured":"Liaw, R., Liang, E., Nishihara, R., Moritz, P., Gonzalez, J., Stoica, I.: Tune: A Research Platform for Distributed Model Selection and Training. arXiv:1807.05118 (2018)"},{"key":"2936_CR21","unstructured":"Lin, J., Lee, G.: Trajectory space factorization for deep video-based 3D human pose estimation. In: British Machine Vision Conference (BMVC) (2019)"},{"key":"2936_CR22","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"2936_CR23","doi-asserted-by":"crossref","unstructured":"Liu, R., Shen, J., Wang, H., Chen, C., Cheung, S.C., Asari, V.: Attention mechanism exploits temporal contexts: real-time 3d human pose reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CPRV), pp. 5064\u20135073 (2020)","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"2936_CR24","unstructured":"Liu, Z., Shun, N., Li, W., Lu, J., Wu, Y., Li, C., Yang, L.: ConvTransformer: a convolutional transformer network for video frame synthesis. arXiv:2011.10185 (2020)"},{"key":"2936_CR25","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J. J.: A simple yet effective baseline for 3d human pose estimation, a simple yet effective baseline for 3d human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"2936_CR26","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., Theobalt, C.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 Fifth International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"2936_CR27","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one? In: Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"2936_CR28","unstructured":"Paaschalis, P., Antonis, A.: PE-former: Pose Estimation Transformer. arXiv:2112.04981 (2021)"},{"key":"2936_CR29","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic Differentiation in PyTorch, NIPS 2017 Workshop on Autodiff (2017)"},{"key":"2936_CR30","doi-asserted-by":"crossref","unstructured":"Pavaalkos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3d human pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"2936_CR31","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3d human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"2936_CR32","doi-asserted-by":"crossref","unstructured":"Raayat Imtia Hossain, M., Little, J.J.: Exploiting temporal information for 3d human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 68\u201384 (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"2936_CR33","doi-asserted-by":"crossref","unstructured":"Sarlin, P.-E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 4937\u20134946 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"2936_CR34","unstructured":"Sebastian, J., Aakanksha, C., Afroz, M., Lukasz, K., Wojciech, G., Henryk, M., Jonni, K.: Sparse is enough in scaling transformers (2021)"},{"key":"2936_CR35","unstructured":"Shuai, H., Wu, L., Liu, Q.: Adaptively Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation. arXiv:2110.05092 (2021)"},{"issue":"12","key":"2936_CR36","first-page":"4","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal, L., Balaan, A.O., Black, M.J.: Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. IEEE Trans. Pattern Anal. Mach. Intell. 87(12), 4\u201327 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"56","key":"2936_CR37","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krihevsky, A., Sutskever, I., Salakhudinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"2936_CR38","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Liang, S., Wei, Y.: Integral human pose regression. arXiv:1711.08229 (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"2936_CR39","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Doue, M., Massa, F., Sablayrolles, A., J\u2019egou, H.: Training data-efficient image transformers and distillation through attention. In: International Conference of Machine Learning (ICML) (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"2936_CR40","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.U., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS), pp. 5998\u20136008 (2017)"},{"key":"2936_CR41","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"2936_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, S., Xiong, Y., Lin, D.: Deep networks with stochastic depth. In: European Conference on Computer Vision (ECCV), pp. 646\u2013661 (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"2936_CR43","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, S., Xiong, Y., Lin, D.: Motion guided 3d pose estimation from videos. arXiv:2004.13985 (2020)","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"2936_CR44","unstructured":"Wu, Z., Liu, Z., Lin, J., Han, S.: Lite transformer with long-short range attention. In: International Conference on Learning Representations (ICLR) (2020)"},{"issue":"7","key":"2936_CR45","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1007\/s00371-019-01740-4","volume":"36","author":"J Wu","year":"2020","unstructured":"Wu, J., Hu, D., Xiang, F., Yuan, X., Su, J.: 3D human pose estimation by depth map. Vis. Comput. 36(7), 1401\u20131410 (2020)","journal-title":"Vis. Comput."},{"key":"2936_CR46","unstructured":"Yeh, R., Hu, Y.T., Schwing, A.: Chirality nets for human pose regression. In: International Conference on Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"2936_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Tay, F., Feng, J., Yan, S.: Tokens-to-token ViT: training vision transformers from scratch on ImageNet. In: IEEE International Conference on Computer Vision (ICCV), pp. 538\u2013547 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"2936_CR48","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Huaang, F., Liu, M., Xu, Q., Lin, S.: Srnet: Improving generalization in 3d human pose estimation with a split-and-recombine approach. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"2936_CR49","doi-asserted-by":"crossref","unstructured":"Zheng, C., Zhu, S., Mendieta, M., Yang, T., Cheng, C., Ding, Z.: 3D human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"2936_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, K., Han, X., Jaing, N., Jia, K., Lu, J.: HEMlets pose: learning part-centric heatmap triplets for accurate 3D human pose estimation. In: International Conference of Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00243"},{"key":"2936_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, K., Han, X., Jiang, N., Jai, K., Lu, J.: HEMlets PoSh: learning part-centric heatmap triplets for 3D human pose and shape estimation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2021)","DOI":"10.1109\/TPAMI.2021.3051173"},{"key":"2936_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02936-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02936-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02936-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T17:08:00Z","timestamp":1712336880000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02936-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,3]]},"references-count":52,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["2936"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02936-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,3]]},"assertion":[{"value":"26 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Both authors Alec Diaz-Arias and Dmitriy Shin declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}