{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T07:24:10Z","timestamp":1794036250209,"version":"4.8.0"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726606","type":"print"},{"value":"9783031726613","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72661-3_21","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:53:46Z","timestamp":1732607626000},"page":"363-382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["EgoExo-Fitness: Towards Egocentric and\u00a0Exocentric Full-Body Action Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5914-5605","authenticated-orcid":false,"given":"Yuan-Ming","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0600-2206","authenticated-orcid":false,"given":"Wei-Jin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5449-6438","authenticated-orcid":false,"given":"An-Lan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8125-8024","authenticated-orcid":false,"given":"Ling-An","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5437-3070","authenticated-orcid":false,"given":"Jing-Ke","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","unstructured":"Akada, H., Wang, J., Shimada, S., Takahashi, M., Theobalt, C., Golyanik, V.: UnrealEgo: a new dataset for robust egocentric 3D human motion capture. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13666. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_1","DOI":"10.1007\/978-3-031-20068-7_1"},{"key":"21_CR2","doi-asserted-by":"publisher","unstructured":"Bansal, S., Arora, C., Jawahar, C.: My view is the best view: procedure learning from egocentric videos. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13673. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19778-9_38","DOI":"10.1007\/978-3-031-19778-9_38"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Soo\u00a0Park, H., Yu, S.X., Shi, J.: Am I a baller? Basketball performance assessment from first-person videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2177\u20132185 (2017)","DOI":"10.1109\/ICCV.2017.239"},{"key":"21_CR4","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: Proceedings of the International Conference on Machine Learning (2021)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Bock, M., Moeller, M., Van\u00a0Laerhoven, K., Kuehne, H.: WEAR: a multimodal dataset for wearable and egocentric video activity recognition. arXiv preprint arXiv:2304.05088 (2023)","DOI":"10.1145\/3699776"},{"key":"21_CR6","doi-asserted-by":"publisher","unstructured":"Cai, Z, et al.: HuMMan: multi-modal 4D human dataset for versatile sensing and modeling. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13667. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20071-7_33","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"21_CR8","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. arXiv preprint arXiv:1808.01340 (2018)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Damen, D., et\u00a0al.: Scaling egocentric vision: the epic-kitchens dataset. In: Proceedings of the European Conference on Computer Vision, pp. 720\u2013736 (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"21_CR11","unstructured":"Damen, D., et\u00a0al.: Rescaling egocentric vision. arXiv preprint arXiv:2006.13256 (2020)"},{"key":"21_CR12","first-page":"13800","volume":"35","author":"J DelPreto","year":"2022","unstructured":"DelPreto, J., et al.: ActionSense: a multimodal dataset and recording framework for human activities using wearable sensors in a kitchen environment. Adv. Neural. Inf. Process. Syst. 35, 13800\u201313813 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Diete, A., Sztyler, T., Stuckenschmidt, H.: Vision and acceleration modalities: partners for recognizing complex activities. In: Proceedings of the IEEE International Conference on Pervasive Computing and Communications Workshops, pp. 101\u2013106. IEEE (2019)","DOI":"10.1109\/PERCOMW.2019.8730690"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Dong, S., Hu, H., Lian, D., Luo, W., Qian, Y., Gao, S.: Weakly supervised video representation learning with unaligned text for sequential videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2437\u20132447 (2023)","DOI":"10.1109\/CVPR52729.2023.00241"},{"key":"21_CR15","unstructured":"Donley, J., et al.: EasyCom: an augmented reality dataset to support algorithms for easy communication in noisy environments. arXiv preprint arXiv:2107.04174 (2021)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Doughty, H., Damen, D., Mayol-Cuevas, W.: Who\u2019s better? Who\u2019s best? Pairwise deep ranking for skill determination. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6057\u20136066 (2018)","DOI":"10.1109\/CVPR.2018.00634"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Doughty, H., Mayol-Cuevas, W., Damen, D.: The pros and cons: rank-aware temporal attention for skill determination in long videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7862\u20137871 (2019)","DOI":"10.1109\/CVPR.2019.00805"},{"key":"21_CR18","unstructured":"Du, J.R., et al.: Weakly-supervised temporal action localization by progressive complementary learning. arXiv preprint arXiv:2206.11011 (2022)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Pirlea, S.C., Olaru, V., Sminchisescu, C.: AIFit: automatic 3D human-interpretable feedback models for fitness training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9919\u20139928 (2021)","DOI":"10.1109\/CVPR46437.2021.00979"},{"key":"21_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/978-3-030-58577-8_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Gao","year":"2020","unstructured":"Gao, J., et al.: An asymmetric modeling for action assessment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 222\u2013238. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_14"},{"key":"21_CR21","unstructured":"Gao, Y., et\u00a0al.: JHU-ISI gesture and skill assessment working set (JIGSAWS): a surgical activity dataset for human motion modeling. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention Workshop (2014)"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Ghoddoosian, R., Dwivedi, I., Agarwal, N., Dariush, B.: Weakly-supervised action segmentation and unseen error detection in anomalous instructional videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10128\u201310138 (2023)","DOI":"10.1109\/ICCV51070.2023.00929"},{"key":"21_CR23","unstructured":"Grauman, K., et\u00a0al.: Ego4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"21_CR24","unstructured":"Grauman, K., et\u00a0al.: Ego-Exo4D: understanding skilled human activity from first-and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Guzov, V., Mir, A., Sattler, T., Pons-Moll, G.: Human POSEitioning system (HPS): 3D human pose estimation and self-localization in large scenes from body-mounted sensors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4318\u20134329 (2021)","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"21_CR26","unstructured":"He, T., et al.: Collaborative weakly supervised video correlation learning for procedure-aware instructional video analysis. arXiv preprint arXiv:2312.11024 (2023)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Hu, H., Dong, S., Zhao, Y., Lian, D., Li, Z., Gao, S.: TransRAC: encoding multi-scale temporal correlation with transformers for repetitive action counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19013\u201319022 (2022)","DOI":"10.1109\/CVPR52688.2022.01843"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Huang, Y., et\u00a0al.: EgoExoLearn: a dataset for bridging asynchronous ego-and exo-centric view of procedural activities in real world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22072\u201322086 (2024)","DOI":"10.1109\/CVPR52733.2024.02084"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, 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)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Jang, Y.K., Cho, N.I.: Self-supervised product quantization for deep unsupervised image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12085\u201312094 (2021)","DOI":"10.1109\/ICCV48922.2021.01187"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Jang, Y., Sullivan, B., Ludwig, C., Gilchrist, I., Damen, D., Mayol-Cuevas, W.: EPIC-Tent: an egocentric video dataset for camping tent assembly. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00547"},{"key":"21_CR32","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Bansal, A., Ma, L., Newcombe, R., Vo, M., Kitani, K.: EgoHumans: an egocentric 3D multi-human benchmark. arXiv preprint arXiv:2305.16487 (2023)","DOI":"10.1109\/ICCV51070.2023.01814"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Kim, D., Saito, K., Oh, T.H., Plummer, B.A., Sclaroff, S., Saenko, K.: CDS: cross-domain self-supervised pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9123\u20139132 (2021)","DOI":"10.1109\/ICCV48922.2021.00899"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Kong, Y., Fu, Y.: Human action recognition and prediction: a survey. Int. J. Comput. Vis. 130, 1366\u20131401 (2022)","DOI":"10.1007\/s11263-022-01594-9"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Kwon, T., Tekin, B., St\u00fchmer, J., Bogo, F., Pollefeys, M.: H2O: two hands manipulating objects for first person interaction recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10138\u201310148 (2021)","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Lei, S.W., et al.: AssistSR: task-oriented video segment retrieval for personal AI assistant. arXiv preprint arXiv:2111.15050 (2021)","DOI":"10.18653\/v1\/2022.findings-emnlp.24"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, K., Wu, J.: Ego-body pose estimation via ego-head pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17142\u201317151 (2023)","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., Rehg, J.M.: In the eye of beholder: joint learning of gaze and actions in first person video. In: Proceedings of the European conference on computer vision (ECCV), pp. 619\u2013635 (2018)","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Vasconcelos, N.: RESOUND: towards action recognition without representation bias. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 513\u2013528 (2018)","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Li, Y.M., Zeng, L.A., Meng, J.K., Zheng, W.S.: Continual action assessment via task-consistent score-discriminative feature distribution modeling. In: IEEE Transactions on Circuits and Systems for Video Technology (2024)","DOI":"10.1109\/TCSVT.2024.3396692"},{"key":"21_CR42","unstructured":"Lin, K.Q., et al.: Egocentric video-language pretraining. Adv. Neural. Inf. Process. Syst. 35, 7575\u20137586 (2022)"},{"key":"21_CR43","unstructured":"Lin, K.Y., et al.: Rethinking clip-based video learners in cross-domain open-vocabulary action recognition. arXiv preprint arXiv:2403.01560 (2024)"},{"issue":"10","key":"21_CR44","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+ D 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR45","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","volume":"31","author":"X Liu","year":"2022","unstructured":"Liu, X., et al.: End-to-end temporal action detection with transformer. IEEE Trans. Image Process. 31, 5427\u20135441 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: HOI4D: a 4D egocentric dataset for category-level human-object interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21013\u201321022 (2022)","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Ng, E., Xiang, D., Joo, H., Grauman, K.: You2Me: inferring body pose in egocentric video via first and second person interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9890\u20139900 (2020)","DOI":"10.1109\/CVPR42600.2020.00991"},{"key":"21_CR48","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Parmar, P., Morris, B.: Action quality assessment across multiple actions. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1468\u20131476. IEEE (2019)","DOI":"10.1109\/WACV.2019.00161"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Parmar, P., Morris, B.T.: What and how well you performed? A multitask learning approach to action quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 304\u2013313 (2019)","DOI":"10.1109\/CVPR.2019.00039"},{"key":"21_CR51","unstructured":"Plizzari, C., et al.: An outlook into the future of egocentric vision. arXiv preprint arXiv:2308.07123 (2023)"},{"key":"21_CR52","doi-asserted-by":"crossref","unstructured":"Possas, R., Caceres, S.P., Ramos, F.: Egocentric activity recognition on a budget. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5967\u20135976 (2018)","DOI":"10.1109\/CVPR.2018.00625"},{"key":"21_CR53","doi-asserted-by":"crossref","unstructured":"Qian, Y., Luo, W., Lian, D., Tang, X., Zhao, P., Gao, S.: SVIP: sequence verification for procedures in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19890\u201319902 (2022)","DOI":"10.1109\/CVPR52688.2022.01927"},{"key":"21_CR54","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Furnari, A., Livatino, S., Farinella, G.M.: The Meccano dataset: understanding human-object interactions from egocentric videos in an industrial-like domain. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1569\u20131578 (2021)","DOI":"10.1109\/WACV48630.2021.00161"},{"key":"21_CR56","doi-asserted-by":"crossref","unstructured":"Ryan, F., Jiang, H., Shukla, A., Rehg, J.M., Ithapu, V.K.: Egocentric auditory attention localization in conversations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14663\u201314674 (2023)","DOI":"10.1109\/CVPR52729.2023.01409"},{"key":"21_CR57","doi-asserted-by":"crossref","unstructured":"Sener, F., et al.: Assembly101: a large-scale multi-view video dataset for understanding procedural activities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21096\u201321106 (2022)","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"21_CR58","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"21_CR59","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: FineGym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"21_CR60","unstructured":"Sigurdsson, G.A., Gupta, A., Schmid, C., Farhadi, A., Alahari, K.: Charades-Ego: a large-scale dataset of paired third and first person videos. arXiv preprint arXiv:1804.09626 (2018)"},{"key":"21_CR61","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: FLAG3D: a 3D fitness activity dataset with language instruction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02117"},{"key":"21_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"21_CR63","unstructured":"De\u00a0la Torre, F., et al.: Guide to the Carnegie Mellon university multimodal activity (CMU-MMAC) database, Technical report CMU-RI-TR-08-22, Robotics Institute, Carnegie Mellon University (2009)"},{"key":"21_CR64","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"21_CR65","doi-asserted-by":"crossref","unstructured":"Wang, B., Zhao, Y., Yang, L., Long, T., Li, X.: Temporal action localization in the deep learning era: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(4) (2023)","DOI":"10.1109\/TPAMI.2023.3330794"},{"key":"21_CR66","doi-asserted-by":"crossref","unstructured":"Wang, J., Luvizon, D., Xu, W., Liu, L., Sarkar, K., Theobalt, C.: Scene-aware egocentric 3D human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13031\u201313040 (2023)","DOI":"10.1109\/CVPR52729.2023.01252"},{"key":"21_CR67","doi-asserted-by":"crossref","unstructured":"Wang, X., et\u00a0al.: HoloAssist: an egocentric human interaction dataset for interactive AI assistants in the real world. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20270\u201320281 (2023)","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"21_CR68","doi-asserted-by":"publisher","unstructured":"Wong, B., et al.: AssistQ: affordance-centric question-driven task completion for egocentric assistant. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13696. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_28","DOI":"10.1007\/978-3-031-20059-5_28"},{"issue":"12","key":"21_CR69","doi-asserted-by":"publisher","first-page":"4578","DOI":"10.1109\/TCSVT.2019.2927118","volume":"30","author":"C Xu","year":"2019","unstructured":"Xu, C., Fu, Y., Zhang, B., Chen, Z., Jiang, Y.G., Xue, X.: Learning to score figure skating sport videos. IEEE Trans. Circuits Syst. Video Technol. 30(12), 4578\u20134590 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"21_CR70","doi-asserted-by":"crossref","unstructured":"Xu, J., Rao, Y., Yu, X., Chen, G., Zhou, J., Lu, J.: FineDiving: a fine-grained dataset for procedure-aware action quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2949\u20132958 (2022)","DOI":"10.1109\/CVPR52688.2022.00296"},{"issue":"5","key":"21_CR71","doi-asserted-by":"publisher","first-page":"2093","DOI":"10.1109\/TVCG.2019.2898650","volume":"25","author":"W Xu","year":"2019","unstructured":"Xu, W., et al.: Mo2Cap2: real-time mobile 3D motion capture with a cap-mounted fisheye camera. IEEE Trans. Vis. Comput. Graph. 25(5), 2093\u20132101 (2019)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"21_CR72","doi-asserted-by":"crossref","unstructured":"Yu, H., Cai, M., Liu, Y., Lu, F.: What I see is what you see: joint attention learning for first and third person video co-analysis. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1358\u20131366 (2019)","DOI":"10.1145\/3343031.3350896"},{"key":"21_CR73","doi-asserted-by":"crossref","unstructured":"Zeng, L.A., et al.: Hybrid dynamic-static context-aware attention network for action assessment in long videos. In: Proceedings of the ACM International Conference on Multimedia, pp. 2526\u20132534 (2020)","DOI":"10.1145\/3394171.3413560"},{"key":"21_CR74","doi-asserted-by":"crossref","unstructured":"Zeng, L.A., Zheng, W.S.: Multimodal action quality assessment. IEEE Trans. Image Process. 33 (2024)","DOI":"10.1109\/TIP.2024.3362135"},{"key":"21_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, C.L., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"21_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: LOGO: a long-form video dataset for group action quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2405\u20132414 (2023)","DOI":"10.1109\/CVPR52729.2023.00238"},{"key":"21_CR77","doi-asserted-by":"publisher","unstructured":"Zhang, S. et al.: EgoBody: human body shape and motion of interacting people from head-mounted devices. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13666. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_11","DOI":"10.1007\/978-3-031-20068-7_11"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72661-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:22:30Z","timestamp":1732609350000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72661-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031726606","9783031726613"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72661-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}