{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T11:37:19Z","timestamp":1725881839956},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319541839"},{"type":"electronic","value":"9783319541846"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-54184-6_22","type":"book-chapter","created":{"date-parts":[[2017,3,9]],"date-time":"2017-03-09T15:44:25Z","timestamp":1489074265000},"page":"352-367","source":"Crossref","is-referenced-by-count":0,"title":["Human Interaction Recognition by Mining Discriminative Patches on Key Frames"],"prefix":"10.1007","author":[{"given":"Dingyi","family":"Shan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laiyun","family":"Qing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,10]]},"reference":[{"key":"22_CR1","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-642-33709-3_6","volume-title":"Computer Vision \u2013 ECCV 2012","author":"S Singh","year":"2012","unstructured":"Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) Computer Vision \u2013 ECCV 2012. LNCS, vol. 7573, pp. 73\u201386. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-33709-3_6"},{"key":"22_CR2","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Mid-level visual element discovery as discriminative mode seeking. In: Advances in Neural Information Processing Systems, pp. 494\u2013502 (2013)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Juneja, M., Vedaldi, A., Jawahar, C., Zisserman, A.: Blocks that shout: distinctive parts for scene classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 923\u2013930 (2013)","DOI":"10.1109\/CVPR.2013.124"},{"key":"22_CR4","unstructured":"Wang, X., Wang, B., Bai, X., Liu, W., Tu, Z.: Max-margin multiple-instance dictionary learning. In: Proceedings of the 30th International Conference on Machine Learning, pp. 846\u2013854 (2013)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3D human pose annotations. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1365\u20131372. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, L., Shen, C., van den Hengel, A.: Mid-level deep pattern mining. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 971\u2013980. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298699"},{"key":"22_CR7","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1109\/TPAMI.2011.228","volume":"34","author":"T Lan","year":"2012","unstructured":"Lan, T., Wang, Y., Yang, W., Robinovitch, S.N., Mori, G.: Discriminative latent models for recognizing contextual group activities. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1549\u20131562 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Recognition of composite human activities through context-free grammar based representation. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1709\u20131718. IEEE (2006)","DOI":"10.1109\/CVPR.2006.242"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Choi, W., Shahid, K., Savarese, S.: Learning context for collective activity recognition. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3273\u20133280. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"22_CR10","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":"22_CR11","doi-asserted-by":"crossref","unstructured":"Su, B., Ding, X.: Linear sequence discriminant analysis: a model-based dimensionality reduction method for vector sequences. In: ICCV, pp. 889\u2013896 (2013)","DOI":"10.1109\/ICCV.2013.115"},{"key":"22_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-319-46493-0_13","volume-title":"Computer Vision \u2013 ECCV 2016","author":"B Su","year":"2016","unstructured":"Su, B., Zhou, J., Ding, X., Wang, H., Wu, Y.: Hierarchical dynamic parsing and encoding for action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 202\u2013217. Springer, Heidelberg (2016). doi: 10.1007\/978-3-319-46493-0_13"},{"key":"22_CR13","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":"22_CR14","doi-asserted-by":"crossref","unstructured":"Brendel, W., Todorovic, S.: Learning spatiotemporal graphs of human activities. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 778\u2013785. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Raptis, M., Kokkinos, I., Soatto, S.: Discovering discriminative action parts from mid-level video representations. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1242\u20131249. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"22_CR16","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). doi: 10.1007\/978-3-642-33718-5_22"},{"key":"22_CR17","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1109\/TPAMI.2014.2303090","volume":"36","author":"Y Kong","year":"2014","unstructured":"Kong, Y., Jia, Y., Fu, Y.: Interactive phrases: semantic descriptions for human interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell. 36, 1775\u20131788 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Spatio-temporal relationship match: video structure comparison for recognition of complex human activities. In: 2009 IEEE 12th International Conference on Computer vision, pp. 1593\u20131600. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Amer, M.R., Todorovic, S.: Sum-product networks for modeling activities with stochastic structure. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1314\u20131321. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247816"},{"key":"22_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10599-4_29"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Xu, Z., Qing, L., Miao, J.: Activity auto-completion: predicting human activities from partial videos. In: ICCV, pp. 3191\u20133199 (2015)","DOI":"10.1109\/ICCV.2015.365"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"22_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"22_CR24","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1\u201327:27 (2011). http:\/\/www.csie.ntu.edu.tw\/cjlin\/libsvm","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"22_CR25","unstructured":"Ryoo, M.S., Aggarwal, J.: Ut-interaction dataset, ICPR contest on semantic description of human activities (SDHA). In: IEEE International Conference on Pattern Recognition Workshops, vol. 2, p. 4 (2010)"},{"key":"22_CR26","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1109\/TIP.2015.2498410","volume":"25","author":"Y Kong","year":"2016","unstructured":"Kong, Y., Fu, Y.: Close human interaction recognition using patch-aware models. IEEE Trans. Image Process. 25, 167\u2013178 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-319-10578-9_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Lan","year":"2014","unstructured":"Lan, T., Chen, T.-C., Savarese, S.: A hierarchical representation for future action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 689\u2013704. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10578-9_45"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Ryoo, M.: Human activity prediction: early recognition of ongoing activities from streaming videos. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1036\u20131043. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"22_CR29","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). doi: 10.1007\/978-3-642-33712-3_51"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Cao, Y., Barrett, D., Barbu, A., Narayanaswamy, S., Yu, H., Michaux, A., Lin, Y., Dickinson, S., Siskind, J., Wang, S.: Recognize human activities from partially observed videos. In: CVPR, pp. 2658\u20132665 (2013)","DOI":"10.1109\/CVPR.2013.343"},{"key":"22_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1007\/978-3-319-10602-1_39","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Kong","year":"2014","unstructured":"Kong, Y., Kit, D., Fu, Y.: A discriminative model with multiple temporal scales for action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 596\u2013611. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10602-1_39"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2016"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-54184-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,19]],"date-time":"2019-09-19T14:43:10Z","timestamp":1568904190000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-54184-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319541839","9783319541846"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-54184-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}