{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:02:44Z","timestamp":1776092564189,"version":"3.50.1"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012489","type":"print"},{"value":"9783030012496","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01249-6_7","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T15:35:46Z","timestamp":1538753746000},"page":"104-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":114,"title":["stagNet: An Attentive Semantic RNN for Group Activity Recognition"],"prefix":"10.1007","author":[{"given":"Mengshi","family":"Qi","sequence":"first","affiliation":[]},{"given":"Jie","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Annan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"7_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv (2016)"},{"issue":"4","key":"7_CR2","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1109\/TPAMI.2015.2465955","volume":"38","author":"MR Amer","year":"2016","unstructured":"Amer, M.R., Todorovic, S.: Sum product networks for activity recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(4), 800\u2013813 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Amer, M.R., Todorovic, S., Fern, A., Zhu, S.C.: Monte carlo tree search for scheduling activity recognition. In: ICCV. IEEE (2013)","DOI":"10.1109\/ICCV.2013.171"},{"key":"7_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-3-642-33765-9_14","volume-title":"Computer Vision \u2013 ECCV 2012","author":"MR Amer","year":"2012","unstructured":"Amer, M.R., Xie, D., Zhao, M., Todorovic, S., Zhu, S.-C.: Cost-sensitive top-down\/bottom-up inference for multiscale activity recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 187\u2013200. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33765-9_14"},{"key":"7_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/978-3-319-10599-4_37","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MR Amer","year":"2014","unstructured":"Amer, M.R., Lei, P., Todorovic, S.: HiRF: hierarchical random field for collective activity recognition in videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 572\u2013585. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_37"},{"key":"7_CR6","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: CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.365"},{"key":"7_CR7","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"7_CR8","unstructured":"Bengio, Y., LeCun, Y., Henderson, D.: Globally trained handwritten word recognizer using spatial representation, convolutional neural networks, and hidden Markov models. In: NIPS. MIT Press (1994)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Cao, C., Liu, X., Yang, Y., Yu, Y.: Look and think twice: capturing top-down visual attention with feedback convolutional neural networks. In: ICCV. IEEE (2015)","DOI":"10.1109\/ICCV.2015.338"},{"key":"7_CR10","unstructured":"Chen, L.C., Schwing, A.G., Yuille, A.L., Urtasun, R.: Learning deep structured models. In: ICLR (2014)"},{"key":"7_CR11","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 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-642-33765-9_16","volume-title":"Computer Vision \u2013 ECCV 2012","author":"W Choi","year":"2012","unstructured":"Choi, W., Savarese, S.: A unified framework for multi-target tracking and collective activity recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 215\u2013230. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33765-9_16"},{"key":"7_CR13","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing?: collective activity classification using spatio-temporal relationship among people. In: ICCV Workshops. IEEE (2009)"},{"key":"7_CR14","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS. MIT Press (2016)"},{"key":"7_CR15","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR. IEEE (2005)"},{"key":"7_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/11744047_33","volume-title":"Computer Vision \u2013 ECCV 2006","author":"N Dalal","year":"2006","unstructured":"Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 428\u2013441. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744047_33"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Deng, Z., Vahdat, A., Hu, H., Mori, G.: Structure inference machines: recurrent neural networks for analyzing relations in group activity recognition. In: CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.516"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR. IEEE (2015)","DOI":"10.21236\/ADA623249"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Hajimirsadeghi, H., Yan, W., Vahdat, A., Mori, G.: Visual recognition by counting instances: a multi-instance cardinality potential kernel. In: CVPR. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298875"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR21","unstructured":"Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning-lecture 6a-overview of mini-batch gradient descent"},{"issue":"8","key":"7_CR22","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Ibrahim, M.S., Muralidharan, S., Deng, Z., Vahdat, A., Mori, G.: A hierarchical deep temporal model for group activity recognition. In: CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.217"},{"issue":"11","key":"7_CR24","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"7_CR26","unstructured":"Krahenbuhl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: NIPS. MIT Press (2011)"},{"key":"7_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS. MIT Press (2012)"},{"issue":"8","key":"7_CR28","doi-asserted-by":"publisher","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(8), 1549\u201362 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Li, S., Zhang, W., Chan, A.B.: Maximum-margin structured learning with deep networks for 3D human pose estimation. In: ICCV. IEEE (2015)","DOI":"10.1109\/ICCV.2015.326"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Li, X., Chuah, M.C.: SBGAR: semantics based group activity recognition. In: CVPR. IEEE (2017)","DOI":"10.1109\/ICCV.2017.313"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Carr, P., Collins, R.T., Liu, Y.: Tracking sports players with context-conditioned motion models. In: CVPR. IEEE (2013)","DOI":"10.1109\/CVPR.2013.239"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, X., Luo, P., Loy, C.C., Tang, X.: Semantic image segmentation via deep parsing network. In: ICCV. IEEE (2015)","DOI":"10.1109\/ICCV.2015.162"},{"issue":"7","key":"7_CR33","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TPAMI.2012.242","volume":"35","author":"WL Lu","year":"2013","unstructured":"Lu, W.L., Ting, J.A., Little, J.J., Murphy, K.P.: Learning to track and identify players from broadcast sports videos. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1704\u20131716 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR34","unstructured":"Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: NIPS. MIT Press (2014)"},{"key":"7_CR35","unstructured":"Mori, G.: Social roles in hierarchical models for human activity recognition. In: CVPR. IEEE (2012)"},{"issue":"1","key":"7_CR36","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1137\/0105003","volume":"5","author":"J Munkres","year":"1957","unstructured":"Munkres, J.: Algorithms for the assignment and transportation problems. J. Soc. Ind. Appl. Math. 5(1), 32\u201338 (1957)","journal-title":"J. Soc. Ind. Appl. Math."},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Qi, M., Wang, Y., Li, A.: Online cross-modal scene retrieval by binary representation and semantic graph. In: MM. ACM (2017)","DOI":"10.1145\/3123266.3123311"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Qin, J., et al.: Binary coding for partial action analysis with limited observation ratios. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.712"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Qin, J., et al.: Zero-shot action recognition with error-correcting output codes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.117"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Huang, J., Abu-El-Haija, S., Gorban, A., Murphy, K., Li, F.F.: Detecting events and key actors in multi-person videos. In: CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.332"},{"issue":"2","key":"7_CR41","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s11263-010-0355-5","volume":"93","author":"MS Ryoo","year":"2011","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Stochastic representation and recognition of high-level group activities: describing structural uncertainties in human activities. Int. J. Comput. Vis. 93(2), 183\u2013200 (2011)","journal-title":"Int. J. Comput. Vis."},{"issue":"6","key":"7_CR42","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"R Shaoqing","year":"2017","unstructured":"Shaoqing, R., Kaiming, H., Ross, G., Jian, S.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Shu, T., Todorovic, S., Zhu, S.C.: CERN: confidence-energy recurrent network for group activity recognition. In: CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.453"},{"key":"7_CR44","unstructured":"Shu, T., Xie, D., Rothrock, B., Todorovic, S.: Joint inference of groups, events and human roles in aerial videos. In: CVPR. IEEE (2015)"},{"key":"7_CR45","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"7_CR46","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: NIPS, vol. 4, pp. 2951\u20132959 (2012)"},{"key":"7_CR47","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: AAAI. AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"7_CR49","unstructured":"Tompson, J., Jain, A., Lecun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: NIPS. MIT Press (2014)"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Wang, M., Ni, B., Yang, X.: Recurrent modeling of interaction context for collective activity recognition. In: CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.783"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Z., Shi, Q., Shen, C., Anton, V.D.H.: Bilinear programming for human activity recognition with unknown MRF graphs. In: CVPR. IEEE (2013)","DOI":"10.1109\/CVPR.2013.221"},{"key":"7_CR52","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"7_CR53","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML. ACM (2015)"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N.: Describing videos by exploiting temporal structure. In: ICCV. IEEE (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, N., Paluri, M., Ranzato, M., Darrell, T., Bourdev, L.: PANDA: pose aligned networks for deep attribute modeling. In: CVPR. IEEE (2014)","DOI":"10.1109\/CVPR.2014.212"},{"key":"7_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sohn, K., Villegas, R., Pan, G., Lee, H.: Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction. In: CVPR. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298621"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV. IEEE (2015)","DOI":"10.1109\/ICCV.2015.179"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01249-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:49:03Z","timestamp":1664930943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01249-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012489","9783030012496"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01249-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}