{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T02:24:43Z","timestamp":1787279083143,"version":"build-2736575974"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100010477","name":"Intuitive Surgical","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010477","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-20-CHIA-0029-01"],"award-info":[{"award-number":["ANR-20-CHIA-0029-01"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1007\/s00138-026-01892-z","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T02:02:15Z","timestamp":1787277735000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-view video-pose pretraining for operating room surgical activity recognition"],"prefix":"10.1007","volume":"37","author":[{"given":"Idris","family":"Hamoud","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1044-038X","authenticated-orcid":false,"given":"Vinkle","family":"Srivastav","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Abdullah","family":"Jamal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Didier","family":"Mutter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omid","family":"Mohareri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"1892_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102306","volume":"76","author":"L Maier-Hein","year":"2022","unstructured":"Maier-Hein, L., Eisenmann, M., Sarikaya, D., M\u00e4rz, K., Collins, T., Malpani, A., Fallert, J., Feussner, H., Giannarou, S., Mascagni, P., et al.: Surgical data science-from concepts toward clinical translation. Med. Image Anal. 76, 102306 (2022)","journal-title":"Med. Image Anal."},{"key":"1892_CR2","doi-asserted-by":"crossref","unstructured":"Rodas, N.L., Padoy, N.: Augmented reality for reducing intraoperative radiation exposure to patients and clinicians during x-ray guided procedures. Mixed and Augmented Reality in. Medicine (2018)","DOI":"10.1201\/9781315157702-15"},{"key":"1892_CR3","first-page":"3","volume":"13","author":"A Ladikos","year":"2010","unstructured":"Ladikos, A., Cagniart, C., Ghotbi, R., Reiser, M., Navab, N.: Estimating radiation exposure in interventional environments. MICCAI 13, 3 (2010)","journal-title":"MICCAI"},{"key":"1892_CR4","unstructured":"Padoy, N., Blum, T., Feu\u00dfner, H., Berger, M., Navab, N.: On-line recognition of surgical activity for monitoring in the operating room. In: AAAI (2008)"},{"key":"1892_CR5","doi-asserted-by":"crossref","unstructured":"Czempiel, T., Paschali, M., Keicher, M., Simson, W., Feu\u00dfner, H., Kim, S.T., Navab, N.: Tecno: Surgical phase recognition with multi-stage temporal convolutional networks. In: MICCAI (2020)","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"1892_CR6","unstructured":"Murali, A., Alapatt, D., Mascagni, P., Vardazaryan, A., Garcia, A., Okamoto, N., Mutter, D., Padoy, N.: Latent graph representations for critical view of safety assessment (2022)"},{"key":"1892_CR7","doi-asserted-by":"crossref","unstructured":"Koksal, G., Holm, G., Farshad, F., Navab, A.N.: Sangria: Surgical video scene graph optimization for surgical workflow prediction. In: MICCAI (2024)","DOI":"10.1007\/978-3-031-83243-7_10"},{"key":"1892_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102224","volume":"74","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Marsic, I., Burd, R.S.: Real-time medical phase recognition using long-term video understanding and progress gate method. Med. Image Anal. 74, 102224 (2021)","journal-title":"Med. Image Anal."},{"key":"1892_CR9","unstructured":"Twinanda, A.P., Winata, P., Gangi, A., De Mathelin, M., Padoy, N.: Multi-stream deep architecture for surgical phase recognition on multi-view rgbd videos (2017)"},{"key":"1892_CR10","doi-asserted-by":"crossref","unstructured":"Sharghi, A., Haugerud, H., Oh, D., Mohareri, O.: Automatic operating room surgical activity recognition for robot-assisted surgery. In: MICCAI (2020)","DOI":"10.1007\/978-3-030-59716-0_37"},{"key":"1892_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-023-03022-w","author":"E \u00d6zsoy","year":"2023","unstructured":"\u00d6zsoy, E., Czempiel, T., \u00d6rnek, E.P., Eck, U., Tombari, F., Navab, N.: Holistic or domain modeling: a semantic scene graph approach. International journal of computer assisted radiology and surgery (2023). https:\/\/doi.org\/10.1007\/s11548-023-03022-w","journal-title":"International journal of computer assisted radiology and surgery"},{"key":"1892_CR12","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision (2021)"},{"key":"1892_CR13","unstructured":"Li, Y., Liang, F., Zhao, L., Cui, Y., Ouyang, W., Shao, J., Yu, F., Yan, J.: Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. In: ICLR (2021)"},{"key":"1892_CR14","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q., Sung, Y.-H., Li, Z., Duerig, T.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916. PMLR (2021)"},{"key":"1892_CR15","first-page":"19769","volume":"36","author":"X Zou","year":"2024","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Wang, J., Wang, L., Gao, J., Lee, Y.J.: Segment everything everywhere all at once. Adv. Neural. Inf. Process. Syst. 36, 19769\u201319782 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1892_CR16","doi-asserted-by":"crossref","unstructured":"Lin, W., Karlinsky, L., Shvetsova, N., Possegger, H., Kozinski, M., Panda, R., Feris, R., Kuehne, H., Bischof, H.: Match, expand and improve: unsupervised finetuning for zero-shot action recognition with language knowledge. In: ICCV, pp. 2851\u20132862. (2023)","DOI":"10.1109\/ICCV51070.2023.00267"},{"key":"1892_CR17","doi-asserted-by":"crossref","unstructured":"Goel, S., Bansal, H., Bhatia, S.K., Rossi, R.A., Vinay, V., Grover, A.: Cyclip: cyclic contrastive language-image pretraining. NeurIPS, (2022). arXiv:2205.14459","DOI":"10.52202\/068431-0486"},{"key":"1892_CR18","doi-asserted-by":"crossref","unstructured":"Geng, Z., Wang, C., Wei, Y., Liu, Z., Li, H., Hu, H.: Human pose as compositional tokens. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00071"},{"key":"1892_CR19","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding (2018). arXiv preprint arXiv:1807.03748"},{"key":"1892_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: CVPR (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1892_CR21","doi-asserted-by":"crossref","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. NeurIPS (2022). arXiv:2203.12602","DOI":"10.52202\/068431-0732"},{"key":"1892_CR22","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C., Yuille, A.L., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"1892_CR23","unstructured":"Srivastav, V.K., Issenhuth, T., Kadkhodamohammadi, A., Mathelin, M., Gangi, A., Padoy, N.: Mvor: a multi-view rgb-d operating room dataset for 2d and 3d human pose estimation (2018). arXiv:1808.08180"},{"key":"1892_CR24","doi-asserted-by":"crossref","unstructured":"Srivastav, V., Gangi, A., Padoy, N.: Self-supervision on unlabelled or data for multi-person 2d\/3d human pose estimation. In: MICCAI (2020)","DOI":"10.1007\/978-3-030-59710-8_74"},{"issue":"2","key":"1892_CR25","first-page":"429","volume":"64","author":"NL Rodas","year":"2016","unstructured":"Rodas, N.L., Barrera, F., Padoy, N.: See it with your own eyes: markerless mobile augmented reality for radiation awareness in the hybrid room. IEEE Trans. Biomed. Eng. 64(2), 429\u2013440 (2016)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"1892_CR26","doi-asserted-by":"publisher","unstructured":"Gershov, S., Mahameed, F., Raz, A., Laufer, S.: More than meets the eye: physicians\u2019 visual attention in the operating room. pp. 11\u201320 (2023). https:\/\/doi.org\/10.1007\/978-3-031-47076-9_2","DOI":"10.1007\/978-3-031-47076-9_2"},{"key":"1892_CR27","unstructured":"Hamoud, I., Jamal, M.A., Srivastav, V., Mutter, D., Padoy, N., Mohareri, O.: St(or)$$^2$$: spatio-temporal object level reasoning for activity recognition in the operating room. In: MIDL (2024)"},{"key":"1892_CR28","doi-asserted-by":"crossref","unstructured":"Jamal, M.A., Mohareri, O.: Multi-modal unsupervised pre-training for surgical operating room workflow analysis. In: Medical Image Computing and Computer Assisted Intervention - MICCAI, (2022)","DOI":"10.1007\/978-3-031-16449-1_43"},{"key":"1892_CR29","doi-asserted-by":"crossref","unstructured":"\u00d6zsoy, E., \u00d6rnek, E.P., Eck, U., Czempiel, T., Tombari, F., Navab, N.: 4d-or: Semantic scene graphs for OR domain modeling. In: MICCAI (2022)","DOI":"10.1007\/978-3-031-16449-1_45"},{"key":"1892_CR30","doi-asserted-by":"crossref","unstructured":"\u00d6zsoy, E., Czempiel, T., Holm, F., Pellegrini, C., Navab, N.: Labrad-or: lightweight memory scene graphs for accurate bimodal reasoning in dynamic operating rooms. In: MICCAI (2023)","DOI":"10.1007\/978-3-031-43996-4_29"},{"key":"1892_CR31","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, 201\u2013211 (1973)","journal-title":"Percept. Psychophys."},{"key":"1892_CR32","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: CVPR, pp. 7291\u20137299. (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"1892_CR33","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: CVPR, pp. 2969\u20132978. (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"1892_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Q., Wang, Y.: Learning discriminative representations for skeleton based action recognition. In: CVPR, pp. 10608\u201310617. (2023)","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"1892_CR35","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: CVPR, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"issue":"2","key":"1892_CR36","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.1109\/TPAMI.2022.3169976","volume":"45","author":"R Dai","year":"2020","unstructured":"Dai, R., Das, S., Sharma, S., Minciullo, L., Garattoni, L., Br\u00e9mond, F., Francesca, G.: Toyota smarthome untrimmed: real-world untrimmed videos for activity detection. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 2533\u20132550 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1892_CR37","doi-asserted-by":"publisher","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. pp. 1110\u20131118 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298714","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"1892_CR38","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)"},{"key":"1892_CR39","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition (2018). arXiv:1801.07455","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1892_CR40","doi-asserted-by":"crossref","unstructured":"Elhayek, A., Aguiar, E., Jain, A., Tompson, J., Pishchulin, L., Andriluka, M., Bregler, C., Schiele, B., Theobalt, C.: Efficient convnet-based marker-less motion capture in general scenes with a low number of cameras. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299005"},{"key":"1892_CR41","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"1892_CR42","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. pp. 9726\u20139735 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1892_CR43","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. NeurIPS 33, 9912\u20139924 (2020). arXiv:2006.09882","journal-title":"NeurIPS"},{"key":"1892_CR44","unstructured":"Grill, J.-B., Strub, F., Altch\u2019e, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.\u00c1., Guo, Z.D., Azar, M.G., Piot, B., Kavukcuoglu, K., Munos, R., Valko, M.: Bootstrap your own latent: a new approach to self-supervised learning. NeurIPS (2020)"},{"key":"1892_CR45","unstructured":"Bao, H., Dong, L., Wei, F.: Beit: Bert pre-training of image transformers. In: ICLR (2021)"},{"key":"1892_CR46","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S.R., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. NeurIPS (2021)"},{"key":"1892_CR47","unstructured":"Du, C., Teng, J., Li, T., Liu, Y., Yuan, T., Wang, Y., Yuan, Y., Zhao, H.: On uni-modal feature learning in supervised multi-modal learning (2023). arXiv:2305.01233"},{"key":"1892_CR48","doi-asserted-by":"crossref","unstructured":"Yang, J., Duan, J., Tran, S., Xu, Y., Chanda, S., Chen, L., Zeng, B., Chilimbi, T.M., Huang, J.: Vision-language pre-training with triple contrastive learning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"1892_CR49","doi-asserted-by":"crossref","unstructured":"Wang, W., Bao, H., Dong, L., Bjorck, J., Peng, Z., Liu, Q., Aggarwal, K., Mohammed, O.K., Singhal, S., Som, S., Wei, F.: Image as a foreign language: beit pretraining for vision and vision-language tasks. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"1892_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Leong, M.C., Li, L., Lin, W.: Pevl: Pose-enhanced vision-language model for fine-grained human action recognition. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01784"},{"key":"1892_CR51","first-page":"38571","volume-title":"Advances in Neural Information Processing Systems","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose: simple vision transformer baselines for human pose estimation. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol. 35, pp. 38571\u201338584. Curran Associates Inc (2022)"},{"key":"1892_CR52","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F.T., Upcroft, B.: Simple online and realtime tracking. In: ICIP (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"1892_CR53","unstructured":"Geng, X., Liu, H., Lee, L., Schuurams, D., Levine, S., Abbeel, P.: Multimodal masked autoencoders learn transferable representations. In: ECCV (2022)"},{"key":"1892_CR54","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. NeurIPS 30, (2017). arXiv:1706.03762"},{"key":"1892_CR55","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., K\u00f6pf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: Pytorch: an imperative style, high-performance deep learning library (2019). arXiv:1912.01703"},{"key":"1892_CR56","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: ICCV (2021). arXiv:2104.11227","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"1892_CR57","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"1892_CR58","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B., G\u00fcl\u00e7ehre, \u00c7., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1179"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01892-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-026-01892-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01892-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T02:02:22Z","timestamp":1787277742000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-026-01892-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":58,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["1892"],"URL":"https:\/\/doi.org\/10.1007\/s00138-026-01892-z","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]},"assertion":[{"value":"23 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest. Nicolas Padoy is co-founder and shareholder of Scialytics.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"142"}}