{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:07:40Z","timestamp":1743034060982,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030687984"},{"type":"electronic","value":"9783030687991"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-68799-1_9","type":"book-chapter","created":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T08:03:53Z","timestamp":1614845033000},"page":"115-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9355-5026","authenticated-orcid":false,"given":"Michail","family":"Tsiaousis","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6265-7276","authenticated-orcid":false,"given":"Gertjan","family":"Burghouts","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1301-3073","authenticated-orcid":false,"given":"Fieke","family":"Hillerstr\u00f6m","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6507-6896","authenticated-orcid":false,"given":"Peter","family":"van der Putten","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,5]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"9_CR2","unstructured":"Ba, J., Kiros, J.R., Hinton, G.E.: Layer normalization. ArXiv abs\/1607.06450 (2016)"},{"key":"9_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-030-01768-2_28","volume-title":"Advances in Intelligent Data Analysis XVII","author":"B van Boven","year":"2018","unstructured":"van Boven, B., van der Putten, P., \u00c5str\u00f6m, A., Khalafi, H., Plaat, A.: Real-time excavation detection at construction sites using deep learning. In: Duivesteijn, W., Siebes, A., Ukkonen, A. (eds.) IDA 2018. LNCS, vol. 11191, pp. 340\u2013352. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01768-2_28"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"9_CR5","unstructured":"Ch\u00e9ron, G., Alayrac, J.B., Laptev, I., Schmid, C.: A flexible model for training action localization with varying levels of supervision. In: Advances in Neural Information Processing Systems 31, pp. 942\u2013953. Curran Associates, Inc. (2018)"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Chesneau, N., Rogez, G., Alahari, K., Schmid, C.: Detecting parts for action localization. ArXiv abs\/1707.06005 (2017)","DOI":"10.5244\/C.31.51"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Jo\u00e3o Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 759\u2013768 (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: 2015 IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR12","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, OpenReview.net (2017)"},{"key":"9_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"9_CR14","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"9_CR15","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s11263-018-1120-4","volume":"127","author":"P Mettes","year":"2019","unstructured":"Mettes, P., Snoek, C.G.: Pointly-supervised action localization. Int. J. Comput. Vision 127(3), 263\u2013281 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR16","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5534\u20135542 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"issue":"6","key":"9_CR18","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"9_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR20","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems 30, pp. 4967\u20134976. Curran Associates, Inc. (2017)"},{"key":"9_CR21","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems 27, pp. 568\u2013576. Curran Associates, Inc. (2014)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Siva, P., Xiang, T.: Weakly supervised action detection. In: Proceedings of the British Machine Vision Conference. BMVA Press (2011)","DOI":"10.5244\/C.25.65"},{"key":"9_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-01252-6_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Sun","year":"2018","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 335\u2013351. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_20"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Ulutan, O., Rallapalli, S., Srivatsa, M., Manjunath, B.S.: Actor conditioned attention maps for video action detection. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 516\u2013525 (2020)","DOI":"10.1109\/WACV45572.2020.9093617"},{"key":"9_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30, pp. 5998\u20136008. Curran Associates, Inc. (2017)"},{"key":"9_CR27","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. ArXiv abs\/1710.10903 (2018)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"9_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-01228-1_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413\u2013431. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: 2015 IEEE International Conference on Computer Vision, pp. 3164\u20133172 (2015)","DOI":"10.1109\/ICCV.2015.362"},{"key":"9_CR31","unstructured":"Weinzaepfel, P., Martin, X., Schmid, C.: Towards weakly-supervised action localization. ArXiv abs\/1605.05197 (2016)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Wu, J., Wang, L., Wang, L., Guo, J., Wu, G.: Learning actor relation graphs for group activity recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9956\u20139966 (2019)","DOI":"10.1109\/CVPR.2019.01020"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tokmakov, P., Hebert, M., Schmid, C.: A structured model for action detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9967\u20139976 (2019)","DOI":"10.1109\/CVPR.2019.01021"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68799-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T08:46:38Z","timestamp":1614847598000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68799-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030687984","9783030687991"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68799-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"5 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPR2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpr2020.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}