{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:19:02Z","timestamp":1777655942655,"version":"3.51.4"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726576","type":"print"},{"value":"9783031726583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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\/978-3-031-72658-3_25","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T03:32:37Z","timestamp":1727839957000},"page":"436-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["On the\u00a0Utility of\u00a03D Hand Poses for\u00a0Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5556-1145","authenticated-orcid":false,"given":"Md Salman","family":"Shamil","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2651-3045","authenticated-orcid":false,"given":"Dibyadip","family":"Chatterjee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5004-6005","authenticated-orcid":false,"given":"Fadime","family":"Sener","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4986-2221","authenticated-orcid":false,"given":"Shugao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,2]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, D., Kim, S., Hong, H., Ko, B.C.: Star-transformer: a spatio-temporal cross attention transformer for human action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3330\u20133339 (2023)","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"25_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"25_CR4","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your VIT but faster. arXiv preprint arXiv:2210.09461 (2022)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Bruce, X., Liu, Y., Chan, K.C.: Multimodal fusion via teacher-student network for indoor action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 3199\u20133207 (2021)","DOI":"10.1609\/aaai.v35i4.16430"},{"issue":"3","key":"25_CR6","first-page":"3522","volume":"45","author":"X Bruce","year":"2022","unstructured":"Bruce, X., Liu, Y., Zhang, X., Zhong, S.H., Chan, K.C.: MMNet: a model-based multimodal network for human action recognition in RGB-D videos. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3522\u20133538 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Caetano, C., Sena, J., Br\u00e9mond, F., Dos\u00a0Santos, J.A., Schwartz, W.R.: Skelemotion: a new representation of skeleton joint sequences based on motion information for 3D action recognition. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.\u00a01\u20138. IEEE (2019)","DOI":"10.1109\/AVSS.2019.8909840"},{"issue":"3","key":"25_CR8","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1109\/TCYB.2017.2756840","volume":"48","author":"C Cao","year":"2017","unstructured":"Cao, C., Zhang, Y., Zhang, C., Lu, H.: Body joint guided 3-D deep convolutional descriptors for action recognition. IEEE Trans. Cybern. 48(3), 1095\u20131108 (2017)","journal-title":"IEEE Trans. Cybern."},{"key":"25_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 Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"25_CR10","unstructured":"Chatterjee, D., Sener, F., Ma, S., Yao, A.: Opening the vocabulary of egocentric actions. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023)"},{"key":"25_CR11","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 183\u2013192 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron, G., Laptev, I., Schmid, C.: P-CNN: pose-based CNN features for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3218\u20133226 (2015)","DOI":"10.1109\/ICCV.2015.368"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Cho, H., Kim, C., Kim, J., Lee, S., Ismayilzada, E., Baek, S.: Transformer-based unified recognition of two hands manipulating objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4769\u20134778 (2023)","DOI":"10.1109\/CVPR52729.2023.00462"},{"key":"25_CR14","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 (ECCV), pp. 720\u2013736 (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"issue":"12","key":"25_CR15","doi-asserted-by":"publisher","first-page":"9703","DOI":"10.1109\/TPAMI.2021.3127885","volume":"44","author":"S Das","year":"2021","unstructured":"Das, S., Dai, R., Yang, D., Bremond, F.: VPN++: rethinking video-pose embeddings for understanding activities of daily living. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9703\u20139717 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-030-58545-7_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Das","year":"2020","unstructured":"Das, S., Sharma, S., Dai, R., Br\u00e9mond, F., Thonnat, M.: VPN: learning video-pose embedding for activities of daily living. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 72\u201390. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_5"},{"key":"25_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"25_CR18","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110\u20131118 (2015)","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969\u20132978 (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"25_CR21","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1007\/978-3-031-20083-0_24","volume-title":"European Conference on Computer Vision","author":"M Fayyaz","year":"2022","unstructured":"Fayyaz, M., et al.: Adaptive token sampling for efficient vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 396\u2013414. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_24"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Gan, M., Liu, J., He, Y., Chen, A., Ma, Q.: Keyframe selection via deep reinforcement learning for skeleton-based gesture recognition. IEEE Robot. Autom. Lett. (2023)","DOI":"10.1109\/LRA.2023.3322645"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Grauman, K.: Anticipative video transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13505\u201313515 (2021)","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"25_CR26","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":"25_CR27","doi-asserted-by":"crossref","unstructured":"Han, S., et al.: Megatrack: monochrome egocentric articulated hand-tracking for virtual reality. ACM Trans. Graph. (ToG) 39(4), 87-1 (2020)","DOI":"10.1145\/3386569.3392452"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Han, S., et\u00a0al.: Umetrack: unified multi-view end-to-end hand tracking for VR. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20139 (2022)","DOI":"10.1145\/3550469.3555378"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Hou, J., Wang, G., Chen, X., Xue, J.H., Zhu, R., Yang, H.: Spatial-temporal attention res-TCN for skeleton-based dynamic hand gesture recognition. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11024-6_18"},{"issue":"3","key":"25_CR31","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/TCSVT.2016.2628339","volume":"28","author":"Y Hou","year":"2016","unstructured":"Hou, Y., Li, Z., Wang, P., Li, W.: Skeleton optical spectra-based action recognition using convolutional neural networks. IEEE Trans. Circuits Syst. Video Technol. 28(3), 807\u2013811 (2016)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR32","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning, pp. 4651\u20134664. PMLR (2021)"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Kazakos, E., Nagrani, A., Zisserman, A., Damen, D.: Epic-fusion: audio-visual temporal binding for egocentric action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5492\u20135501 (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"key":"25_CR34","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":"25_CR35","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 156\u2013165 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Lee, C.J., et\u00a0al.: Echowrist: continuous hand pose tracking and hand-object interaction recognition using low-power active acoustic sensing on a wristband. arXiv preprint arXiv:2401.17409 (2024)","DOI":"10.1145\/3613904.3642910"},{"issue":"4","key":"25_CR37","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.1109\/TCDS.2021.3126637","volume":"14","author":"C Li","year":"2021","unstructured":"Li, C., Li, S., Gao, Y., Zhang, X., Li, W.: A two-stream neural network for pose-based hand gesture recognition. IEEE Trans. Cogn. Dev. Syst. 14(4), 1594\u20131603 (2021)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"25_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107356","volume":"104","author":"J Li","year":"2020","unstructured":"Li, J., Xie, X., Pan, Q., Cao, Y., Zhao, Z., Shi, G.: SGM-Net: skeleton-guided multimodal network for action recognition. Pattern Recogn. 104, 107356 (2020)","journal-title":"Pattern Recogn."},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Chen, X., Zhang, Y., Wang, Y., Tian, Q.: Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3595\u20133603 (2019)","DOI":"10.1109\/CVPR.2019.00371"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"issue":"10","key":"25_CR41","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":"25_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, S., Gowda, M.: Neuropose: 3D hand pose tracking using EMG wearables. In: Proceedings of the Web Conference 2021, pp. 1471\u20131482 (2021)","DOI":"10.1145\/3442381.3449890"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 143\u2013152 (2020)","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Ma, J., Damen, D.: Hand-object interaction reasoning. In: 2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/AVSS56176.2022.9959207"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Ohkawa, T., He, K., Sener, F., Hodan, T., Tran, L., Keskin, C.: Assemblyhands: towards egocentric activity understanding via 3D hand pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12999\u201313008 (2023)","DOI":"10.1109\/CVPR52729.2023.01249"},{"key":"25_CR47","unstructured":"Patrick, M., et al.: Keeping your eye on the ball: trajectory attention in video transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12493\u201312506 (2021)"},{"key":"25_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-030-68796-0_50","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"C Plizzari","year":"2021","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Spatial temporal transformer network for skeleton-based action recognition. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12663, pp. 694\u2013701. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68796-0_50"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., Feichtenhofer, C., Malik, J.: On the benefits of 3D pose and tracking for human action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 640\u2013649 (2023)","DOI":"10.1109\/CVPR52729.2023.00069"},{"issue":"4","key":"25_CR50","doi-asserted-by":"publisher","first-page":"7823","DOI":"10.1109\/LRA.2021.3101822","volume":"6","author":"A Sabater","year":"2021","unstructured":"Sabater, A., Alonso, I., Montesano, L., Murillo, A.C.: Domain and view-point agnostic hand action recognition. IEEE Robot. Autom. Lett. 6(4), 7823\u20137830 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"25_CR51","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":"25_CR52","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 Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.F.: Understanding human hands in contact at internet scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9869\u20139878 (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"25_CR55","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"25_CR56","doi-asserted-by":"crossref","unstructured":"Soo\u00a0Kim, T., Reiter, A.: Interpretable 3D human action analysis with temporal convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 20\u201328 (2017)","DOI":"10.1109\/CVPRW.2017.207"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"25_CR59","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588\u2013595 (2014)","DOI":"10.1109\/CVPR.2014.82"},{"key":"25_CR61","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 98\u2013106 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"25_CR62","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131297. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247813"},{"issue":"17","key":"25_CR63","doi-asserted-by":"publisher","first-page":"19157","DOI":"10.1109\/JSEN.2021.3089705","volume":"21","author":"X Weiyao","year":"2021","unstructured":"Weiyao, X., Muqing, W., Min, Z., Ting, X.: Fusion of skeleton and RGB features for RGB-D human action recognition. IEEE Sens. J. 21(17), 19157\u201319164 (2021)","journal-title":"IEEE Sens. J."},{"key":"25_CR64","doi-asserted-by":"crossref","unstructured":"Wen, Y., Pan, H., Yang, L., Pan, J., Komura, T., Wang, W.: Hierarchical temporal transformer for 3D hand pose estimation and action recognition from egocentric RGB videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21243\u201321253 (2023)","DOI":"10.1109\/CVPR52729.2023.02035"},{"key":"25_CR65","doi-asserted-by":"crossref","unstructured":"Wen, Y., Tang, Z., Pang, Y., Ding, B., Liu, M.: Interactive spatiotemporal token attention network for skeleton-based general interactive action recognition. arXiv preprint arXiv:2307.07469 (2023)","DOI":"10.1109\/IROS55552.2023.10342472"},{"key":"25_CR66","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., et al.: Memvit: memory-augmented multiscale vision transformer for efficient long-term video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13587\u201313597 (2022)","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"25_CR67","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"25_CR68","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"25_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, S., Liu, X., Xiao, J.: On geometric features for skeleton-based action recognition using multilayer LSTM networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 148\u2013157. IEEE (2017)","DOI":"10.1109\/WACV.2017.24"},{"issue":"8","key":"25_CR70","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.1109\/TNNLS.2019.2935173","volume":"31","author":"X Zhang","year":"2019","unstructured":"Zhang, X., Xu, C., Tian, X., Tao, D.: Graph edge convolutional neural networks for skeleton-based action recognition. IEEE Trans. Neural Netw. Learn. Syst. 31(8), 3047\u20133060 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"25_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wu, B., Li, W., Duan, L., Gan, C.: STST: spatial-temporal specialized transformer for skeleton-based action recognition. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3229\u20133237 (2021)","DOI":"10.1145\/3474085.3475473"}],"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\/978-3-031-72658-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T23:53:29Z","timestamp":1732838009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72658-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"ISBN":["9783031726576","9783031726583"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72658-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,2]]},"assertion":[{"value":"2 October 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"}}]}}