{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T16:57:05Z","timestamp":1648832225363},"reference-count":38,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2020,6,1]]},"DOI":"10.1587\/transinf.2019mvp0008","type":"journal-article","created":{"date-parts":[[2020,5,31]],"date-time":"2020-05-31T22:09:59Z","timestamp":1590962999000},"page":"1209-1216","source":"Crossref","is-referenced-by-count":1,"title":["Heatmapping of Group People Involved in the Group Activity"],"prefix":"10.1587","volume":"E103.D","author":[{"given":"Kohei","family":"SENDO","sequence":"first","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norimichi","family":"UKITA","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] H. Idrees, A.R. Zamir, Y.-G. Jiang, A. Gorban, I. Laptev, R. Sukthankar, and M. Shah, \u201cThe THUMOS challenge on action recognition for videos \u201cin the wild\u201d,\u201d CVIU, vol.155, pp.1-23, 2017. 10.1016\/j.cviu.2016.10.018","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] S. Herath, M.T. Harandi, and F. Porikli, \u201cGoing deeper into action recognition: A survey,\u201d Image Vision Comput., vol.60, pp.4-21, 2017. 10.1016\/j.imavis.2017.01.010","DOI":"10.1016\/j.imavis.2017.01.010"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] Z. Deng, A. Vahdat, H. Hu, and G. Mori, \u201cStructure inference machines: Recurrent neural networks for analyzing relations in group activity recognition,\u201d CVPR, pp.4772-4781, 2016. 10.1109\/cvpr.2016.516","DOI":"10.1109\/CVPR.2016.516"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] M.S. Ibrahim, S. Muralidharan, Z. Deng, A. Vahdat, and G. Mori, \u201cA hierarchical deep temporal model for group activity recognition,\u201d CVPR, pp.1971-1980, 2016. 10.1109\/cvpr.2016.217","DOI":"10.1109\/CVPR.2016.217"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] M.S. Ibrahim and G. Mori, \u201cHierarchical relational networks for group activity recognition and retrieval,\u201d ECCV, vol.11207, pp.742-758, 2018. 10.1007\/978-3-030-01219-9_44","DOI":"10.1007\/978-3-030-01219-9_44"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] M. Qi, J. Qin, A. Li, Y. Wang, J. Luo, and L.V. Gool, \u201cstagnet: An attentive semantic RNN for group activity recognition,\u201d ECCV, vol.11214, pp.104-120, 2018. 10.1007\/978-3-030-01249-6_7","DOI":"10.1007\/978-3-030-01249-6_7"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] T. Lan, Y. Wang, W. Yang, S.N. Robinovitch, and G. Mori, \u201cDiscriminative latent models for recognizing contextual group activities,\u201d PAMI, vol.34, no.8, pp.1549-1562, 2012. 10.1109\/tpami.2011.228","DOI":"10.1109\/TPAMI.2011.228"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] M.R. Amer, P. Lei, and S. Todorovic, \u201cHirf: Hierarchical random field for collective activity recognition in videos,\u201d ECCV, vol.8694, pp.572-585, 2014. 10.1007\/978-3-319-10599-4_37","DOI":"10.1007\/978-3-319-10599-4_37"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] Z. Wang, Q. Shi, C. Shen, and A. van den Hengel, \u201cBilinear programming for human activity recognition with unknown MRF graphs,\u201d CVPR, pp.1690-1697, 2013. 10.1109\/cvpr.2013.221","DOI":"10.1109\/CVPR.2013.221"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] W. Choi and S. Savarese, \u201cA unified framework for multi-target tracking and collective activity recognition,\u201d ECCV, vol.7575, pp.215-230, 2012. 10.1007\/978-3-642-33765-9_16","DOI":"10.1007\/978-3-642-33765-9_16"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] M.R. Amer, D. Xie, M. Zhao, S. Todorovic, and S.-C. Zhu, \u201cCost-sensitive top-down\/bottom-up inference for multiscale activity recognition,\u201d ECCV, vol.7575, pp.187-200, 2012. 10.1007\/978-3-642-33765-9_14","DOI":"10.1007\/978-3-642-33765-9_14"},{"key":"12","unstructured":"[12] T. Shu, D. Xie, B. Rothrock, S. Todorovic, and S.-C. Zhu, \u201cJoint inference of groups, events and human roles in aerial videos,\u201d CVPR, pp.4576-4584, 2015. 10.1109\/cvpr.2015.7299088"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] G. Guo and A. Lai, \u201cA survey on still image based human action recognition,\u201d Pattern Recognition, vol.47, no.10, pp.3343-3361, 2014. 10.1016\/j.patcog.2014.04.018","DOI":"10.1016\/j.patcog.2014.04.018"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] N. Ukita, \u201cPose estimation with action classification using global-and-pose features and fine-grained action-specific pose models,\u201d IEICE Transactions, vol.E101-D, no.3, pp.758-766, 2018. 10.1587\/transinf.2017edp7204","DOI":"10.1587\/transinf.2017EDP7204"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] B.X. Nie, C. Xiong, and S.-C. Zhu, \u201cJoint action recognition and pose estimation from video,\u201d CVPR, pp.1293-1301, 2015. 10.1109\/cvpr.2015.7298734","DOI":"10.1109\/CVPR.2015.7298734"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] D.C. Luvizon, D. Picard, and H. Tabia, \u201c2d\/3d pose estimation and action recognition using multitask deep learning,\u201d CVPR, pp.5137-5146, 2018. 10.1109\/cvpr.2018.00539","DOI":"10.1109\/CVPR.2018.00539"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] K. Sendo and N. Ukita, \u201cHeatmapping of people involved in group activities,\u201d MVA, pp.1-6, 2019. 10.23919\/mva.2019.8757971","DOI":"10.23919\/MVA.2019.8757971"},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] W.-L. Lu, J.-A. Ting, J.J. Little, and K.P. Murphy, \u201cLearning to track and identify players from broadcast sports videos,\u201d PAMI, vol.35, no.7, pp.1704-1716, 2013. 10.1109\/tpami.2012.242","DOI":"10.1109\/TPAMI.2012.242"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] N. Ukita, Y. Moriguchi, and N. Hagita, \u201cPeople re-identification across non-overlapping cameras using group features,\u201d CVIU, vol.144, pp.228-236, 2016. 10.1016\/j.cviu.2015.06.011","DOI":"10.1016\/j.cviu.2015.06.011"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] B. Zhou, A. Khosla, \u00c0. Lapedriza, A. Oliva, and A. Torralba, \u201cLearning deep features for discriminative localization,\u201d CVPR, pp.2921-2929, 2016. 10.1109\/cvpr.2016.319","DOI":"10.1109\/CVPR.2016.319"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] V. Ramanishka, A. Das, J. Zhang, and K. Saenko, \u201cTop-down visual saliency guided by captions,\u201d CVPR, pp.3135-3144, 2017. 10.1109\/cvpr.2017.334","DOI":"10.1109\/CVPR.2017.334"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] S.-E. Wei, V. Ramakrishna, T. Kanade, and Y. Sheikh, \u201cConvolutional pose machines,\u201d CVPR, pp.4724-4732, 2016. 10.1109\/cvpr.2016.511","DOI":"10.1109\/CVPR.2016.511"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] H. Law and J. Deng, \u201cCornernet: Detecting objects as paired keypoints,\u201d ECCV, pp.765-781, 2018.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] J. Pan, E. Sayrol, X. Gir\u00f3-I-Nieto, K. McGuinness, and N.E. O'Connor, \u201cShallow and deep convolutional networks for saliency prediction,\u201d CVPR, pp.598-606, 2016. 10.1109\/cvpr.2016.71","DOI":"10.1109\/CVPR.2016.71"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S.E. Reed, C.-Y. Fu, and A.C. Berg, \u201cSSD: single shot multibox detector,\u201d ECCV, vol.9905, pp.21-37, 2016. 10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] H. Pirsiavash, D. Ramanan, and C.C. Fowlkes, \u201cGlobally-optimal greedy algorithms for tracking a variable number of objects,\u201d CVPR, pp.1201-1208, 2011. 10.1109\/cvpr.2011.5995604","DOI":"10.1109\/CVPR.2011.5995604"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] C. Feichtenhofer, A. Pinz, and A. Zisserman, \u201cConvolutional two-stream network fusion for video action recognition,\u201d CVPR, pp.1933-1941, 2016. 10.1109\/cvpr.2016.213","DOI":"10.1109\/CVPR.2016.213"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] C. Vondrick, D.J. Patterson, and D. Ramanan, \u201cEfficiently scaling up crowdsourced video annotation,\u201d IJCV, vol.101, no.1, pp.184-204, 2013. 10.1007\/s11263-012-0564-1","DOI":"10.1007\/s11263-012-0564-1"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] Z. Cao, T. Simon, S.-E. Wei, and Y. Sheikh, \u201cRealtime multi-person 2d pose estimation using part affinity fields,\u201d CVPR, pp.1302-1310, 2017. 10.1109\/cvpr.2017.143","DOI":"10.1109\/CVPR.2017.143"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] Y. Kawana, N. Ukita, J.-B. Huang, and M.-H. Yang, \u201cEnsemble convolutional neural networks for pose estimation,\u201d CVIU, vol.169, pp.62-74, 2018. 10.1016\/j.cviu.2017.12.005","DOI":"10.1016\/j.cviu.2017.12.005"},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] N. Ukita and Y. Uematsu, \u201cSemi- and weakly-supervised human pose estimation,\u201d CVIU, vol.170, pp.67-78, 2018. 10.1016\/j.cviu.2018.02.003","DOI":"10.1016\/j.cviu.2018.02.003"},{"key":"32","doi-asserted-by":"publisher","unstructured":"[32] K. Greff, R.K. Srivastava, J. Koutn\u00edk, B.R. Steunebrink, and J. Schmidhuber, \u201cLSTM: A search space odyssey,\u201d IEEE Trans. Neural Netw. Learning Syst., vol.28, no.10, pp.2222-2232, 2017. 10.1109\/tnnls.2016.2582924","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] D. Tran, L.D. Bourdev, R. Fergus, L. Torresani, and M. Paluri, \u201cLearning spatiotemporal features with 3d convolutional networks,\u201d ICCV, pp.4489-4497, 2015. 10.1109\/iccv.2015.510","DOI":"10.1109\/ICCV.2015.510"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] L. Wang, Y. Xiong, Z. Wang, Y. Qiao, D. Lin, X. Tang, and L.V. Gool, \u201cTemporal segment networks: Towards good practices for deep action recognition,\u201d ECCV, vol.9912, pp.20-36, 2016. 10.1007\/978-3-319-46484-8_2","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"35","doi-asserted-by":"publisher","unstructured":"[35] N. Ukita and A. Okada, \u201cHigh-order framewise smoothness-constrained globally-optimal tracking,\u201d CVIU, vol.153, pp.130-142, 2016. 10.1016\/j.cviu.2016.05.012","DOI":"10.1016\/j.cviu.2016.05.012"},{"key":"36","doi-asserted-by":"publisher","unstructured":"[36] S. Chen, B. Song, J. Guo, Y. Zhang, X. Du, and M. Guizani, \u201cFPAN: fine-grained and progressive attention localization network for data retrieval,\u201d Computer Networks, vol.143, pp.98-111, 2018. 10.1016\/j.comnet.2018.07.011","DOI":"10.1016\/j.comnet.2018.07.011"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] M. Berman, A.R. Triki, and M.B. Blaschko, \u201cThe lov\u00e1sz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks,\u201d CVPR, pp.4413-4421, 2018. 10.1109\/cvpr.2018.00464","DOI":"10.1109\/CVPR.2018.00464"},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] J. Yu, Y. Jiang, Z. Wang, Z. Cao, and T.S. Huang, \u201cUnitbox: An advanced object detection network,\u201d ACM MM, pp.516-520, 2016. 10.1145\/2964284.2967274","DOI":"10.1145\/2964284.2967274"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0008\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,6]],"date-time":"2020-06-06T03:28:00Z","timestamp":1591414080000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0008\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,1]]},"references-count":38,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019mvp0008","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,1]]}}}