{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:39:19Z","timestamp":1743039559257,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819947607"},{"type":"electronic","value":"9789819947614"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-4761-4_17","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T16:02:10Z","timestamp":1690732930000},"page":"193-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["InterFormer: Human Interaction Understanding with Deformed Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5025-7062","authenticated-orcid":false,"given":"Di","family":"He","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0954-2757","authenticated-orcid":false,"given":"Zexing","family":"Du","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5224-906X","authenticated-orcid":false,"given":"Xue","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3439-0644","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"17_CR1","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":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bagautdinov, T., Alahi, A., Fleuret, F., Fua, P., Savarese, S.: Social scene understanding: End-to-end multi-person action localization and collective activity recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4315\u20134324 (2017)","DOI":"10.1109\/CVPR.2017.365"},{"key":"17_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? (2021)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"17_CR5","unstructured":"Diba, A., et al.: Temporal 3d convnets: New architecture and transfer learning for video classification. arXiv preprint arXiv:1711.08200 (2017)"},{"key":"17_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-030-58545-7_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Ehsanpour","year":"2020","unstructured":"Ehsanpour, M., Abedin, A., Saleh, F., Shi, J., Reid, I., Rezatofighi, H.: Joint learning of social groups, individuals action and sub-group activities in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 177\u2013195. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_11"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Sanford, R., Javan, M., Snoek, C.G.: Actor-transformers for group activity recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 839\u2013848 (2020)","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"issue":"8","key":"17_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3472290","volume":"54","author":"F Gu","year":"2021","unstructured":"Gu, F., Chung, M.H., Chignell, M., Valaee, S., Zhou, B., Liu, X.: A survey on deep learning for human activity recognition. ACM Comput. Surv. 54(8), 1\u201334 (2021). https:\/\/doi.org\/10.1145\/3472290","journal-title":"ACM Comput. Surv."},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Han, M., Zhang, D.J., Wang, Y., Yan, R., Yao, L., Chang, X., Qiao, Y.: Dual-ai: dual-path actor interaction learning for group activity recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2990\u20132999 (2022)","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Hu, G., Cui, B., He, Y., Yu, S.: Progressive relation learning for group activity recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 980\u2013989 (2020)","DOI":"10.1109\/CVPR42600.2020.00106"},{"key":"17_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-642-33718-5_22","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y Kong","year":"2012","unstructured":"Kong, Y., Jia, Y., Fu, Y.: Learning human interaction by interactive phrases. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 300\u2013313. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_22"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Cao, Q., Liu, L., Yang, K., Liu, S., Hou, J., Yi, S.: Groupformer: Group activity recognition with clustered spatial-temporal transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13668\u201313677 (2021)","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"17_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-58452-8_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"RRA Pramono","year":"2020","unstructured":"Pramono, R.R.A., Chen, Y.T., Fang, W.H.: Empowering relational network by self-attention augmented conditional random fields for group activity recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 71\u201390. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_5"},{"issue":"2","key":"17_CR18","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1109\/TCSVT.2019.2894161","volume":"30","author":"M Qi","year":"2019","unstructured":"Qi, M., Wang, Y., Qin, J., Li, A., Luo, J., Van Gool, L.: Stagnet: An attentive semantic rnn for group activity and individual action recognition. IEEE Trans. Circuits Syst. Video Technol. 30(2), 549\u2013565 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: UT-Interaction Dataset, ICPR contest on Semantic Description of Human Activities (SDHA). http:\/\/cvrc.ece.utexas.edu\/SDHA2010\/Human_Interaction.html (2010)","DOI":"10.1007\/978-3-642-17711-8_28"},{"key":"17_CR21","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems, vol. 27 (2014)"},{"key":"17_CR22","unstructured":"Su, W., et al.: Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6479\u20136488 (2018)","DOI":"10.1109\/CVPR.2018.00678"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: A joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"17_CR26","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"17_CR27","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":"17_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"17_CR29","doi-asserted-by":"publisher","first-page":"6240","DOI":"10.1109\/TIP.2021.3093383","volume":"30","author":"Z Wang","year":"2021","unstructured":"Wang, Z., Ge, J., Guo, D., Zhang, J., Lei, Y., Chen, S.: Human interaction understanding with joint graph decomposition and node labeling. IEEE Trans. Image Process. 30, 6240\u20136254 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3093383","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR30","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.neucom.2018.09.031","volume":"321","author":"Z Wang","year":"2018","unstructured":"Wang, Z., et al.: Understanding human activities in videos: A joint action and interaction learning approach. Neurocomputing 321, 216\u2013226 (2018)","journal-title":"Neurocomputing"},{"issue":"8","key":"17_CR31","doi-asserted-by":"publisher","first-page":"1647","DOI":"10.1109\/TCSVT.2016.2539699","volume":"27","author":"Z Wang","year":"2017","unstructured":"Wang, Z., Liu, S., Zhang, J., Chen, S., Guan, Q.: A spatio-temporal crf for human interaction understanding. IEEE Trans. Circuits Syst. Video Technol. 27(8), 1647\u20131660 (2017). https:\/\/doi.org\/10.1109\/TCSVT.2016.2539699","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., Meng, J., Guo, D., Zhang, J., Shi, J.Q., Chen, S.: Consistency-aware graph network for human interaction understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13369\u201313378 (2021)","DOI":"10.1109\/ICCV48922.2021.01312"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Wu, J., Wang, L., Wang, L., Guo, J., Wu, G.: Learning actor relation graphs for group activity recognition. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp. 9964\u20139974 (2019)","DOI":"10.1109\/CVPR.2019.01020"},{"key":"17_CR34","doi-asserted-by":"publisher","first-page":"65689","DOI":"10.1109\/ACCESS.2020.2979742","volume":"8","author":"D Xu","year":"2020","unstructured":"Xu, D., Fu, H., Wu, L., Jian, M., Wang, D., Liu, X.: Group activity recognition by using effective multiple modality relation representation with temporal-spatial attention. IEEE Access 8, 65689\u201365698 (2020)","journal-title":"IEEE Access"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Ye, H.J., Hu, H., Zhan, D.C., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8808\u20138817 (2020)","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"17_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4761-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T23:18:51Z","timestamp":1690931931000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4761-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819947607","9789819947614"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4761-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2023a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2023\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}