{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T06:08:08Z","timestamp":1769926088675,"version":"3.49.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198052","type":"print"},{"value":"9783031198069","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19806-9_35","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:11:54Z","timestamp":1666221114000},"page":"605-622","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["IGFormer: Interaction Graph Transformer for\u00a0Skeleton-Based Human Interaction Recognition"],"prefix":"10.1007","author":[{"given":"Yunsheng","family":"Pang","sequence":"first","affiliation":[]},{"given":"Qiuhong","family":"Ke","sequence":"additional","affiliation":[]},{"given":"Hossein","family":"Rahmani","sequence":"additional","affiliation":[]},{"given":"James","family":"Bailey","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"35_CR1","doi-asserted-by":"publisher","unstructured":"Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. 43(3), 16:1\u201316:43 (2011). https:\/\/doi.org\/10.1145\/1922649.1922653","DOI":"10.1145\/1922649.1922653"},{"key":"35_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 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W.: Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13359\u201313368 (2021)","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"35_CR4","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"35_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Y., Wang, L.: Skeleton based action recognition with convolutional neural network. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 579\u2013583. IEEE (2015)","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"35_CR7","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)"},{"key":"35_CR8","doi-asserted-by":"publisher","unstructured":"Ji, Y., Ye, G., Cheng, H.: Interactive body part contrast mining for human interaction recognition. In: 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 1\u20136 (2014). https:\/\/doi.org\/10.1109\/ICMEW.2014.6890714","DOI":"10.1109\/ICMEW.2014.6890714"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: Proceedings of the IEEE Conference on Computer Vision And Pattern Recognition, pp. 3288\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Kim, T.S., Reiter, A.: Interpretable 3D human action analysis with temporal convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1623\u20131631. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.207"},{"key":"35_CR11","unstructured":"Li, B., Dai, Y., Cheng, X., Chen, H., Lin, Y., He, M.: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 601\u2013604. IEEE (2017)"},{"key":"35_CR12","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":"35_CR13","doi-asserted-by":"crossref","unstructured":"Li, S., Li, W., Cook, C., Zhu, C., Gao, Y.: Independently recurrent neural network (IndRNN): building a longer and deeper RNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5457\u20135466 (2018)","DOI":"10.1109\/CVPR.2018.00572"},{"key":"35_CR14","unstructured":"Liu, H., Tu, J., Liu, M.: Two-stream 3D convolutional neural network for skeleton-based action recognition. arXiv preprint arXiv:1705.08106 (2017)"},{"issue":"10","key":"35_CR15","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":"35_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Wang, G., Duan, L.Y., Kot, A.C.: Skeleton-based online action prediction using scale selection network. IEEE Trans. Pattern Anal. Mach. Intell. 42(6), 1453\u20131467 (2019)","DOI":"10.1109\/TPAMI.2019.2898954"},{"key":"35_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-319-46487-9_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Liu","year":"2016","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50"},{"issue":"4","key":"35_CR18","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/tip.2017.2785279","volume":"27","author":"J Liu","year":"2017","unstructured":"Liu, J., Wang, G., Duan, L.Y., Abdiyeva, K., Kot, A.C.: Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Trans. Image Process. 27(4), 1586\u20131599 (2017). https:\/\/doi.org\/10.1109\/tip.2017.2785279","journal-title":"IEEE Trans. Image Process."},{"key":"35_CR19","doi-asserted-by":"publisher","unstructured":"Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3671\u20133680 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.391","DOI":"10.1109\/CVPR.2017.391"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1647\u20131656 (2017)","DOI":"10.1109\/CVPR.2017.391"},{"key":"35_CR21","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":"35_CR22","doi-asserted-by":"crossref","unstructured":"Perez, M., Liu, J., Kot, A.C.: Interaction relational network for mutual action recognition. IEEE Trans. Multimedia 24, 366\u2013376 (2021)","DOI":"10.1109\/TMM.2021.3050642"},{"key":"35_CR23","doi-asserted-by":"publisher","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Skeleton-based action recognition via spatial and temporal transformer networks. Comput. Vis. Image Underst. 208\u2013209, 103219 (2021). https:\/\/doi.org\/10.1016\/j.cviu.2021.103219. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314221000631","DOI":"10.1016\/j.cviu.2021.103219"},{"key":"35_CR24","doi-asserted-by":"publisher","unstructured":"Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6) 976\u2013990 (2010). https:\/\/doi.org\/10.1016\/j.imavis.2009.11.014","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Raptis, M., Sigal, L.: Poselet key-framing: a model for human activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2650\u20132657 (2013)","DOI":"10.1109\/CVPR.2013.342"},{"key":"35_CR26","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 (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"35_CR27","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":"35_CR28","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Vahdat, A., Gao, B., Ranjbar, M., Mori, G.: A discriminative key pose sequence model for recognizing human interactions. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1729\u20131736. IEEE (2011)","DOI":"10.1109\/ICCVW.2011.6130458"},{"key":"35_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"35_CR32","doi-asserted-by":"publisher","unstructured":"Yun, K., Honorio, J., Chattopadhyay, D., Berg, T.L., Samaras, D.: Two-person interaction detection using body-pose features and multiple instance learning. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 28\u201335 (2012). https:\/\/doi.org\/10.1109\/CVPRW.2012.6239234","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2117\u20132126 (2017)","DOI":"10.1109\/ICCV.2017.233"},{"key":"35_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-642-33712-3_51","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y Zhang","year":"2012","unstructured":"Zhang, Y., Liu, X., Chang, M.-C., Ge, W., Chen, T.: Spatio-temporal phrases for activity recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 707\u2013721. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_51"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10451"},{"key":"35_CR37","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"35_CR38","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19806-9_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T23:18:11Z","timestamp":1666394291000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19806-9_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198052","9783031198069"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19806-9_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}