{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:48:37Z","timestamp":1783439317695,"version":"3.54.6"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012519","type":"print"},{"value":"9783030012526","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\/978-3-030-01252-6_20","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T13:48:05Z","timestamp":1538747285000},"page":"335-351","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":141,"title":["Actor-Centric Relation Network"],"prefix":"10.1007","author":[{"given":"Chen","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Shrivastava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carl","family":"Vondrick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Murphy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Sukthankar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Bell, S., Lawrence Zitnick, C., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.314"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.: SST: single-stream temporal action proposals. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.675"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the Kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Dai, X., Singh, B., Zhang, G., Davis, L.S., Chen, Y.Q.: Temporal context network for activity localization in videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.610"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"20_CR8","unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: NIPS (2017)"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object intaractions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"20_CR14","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv:1505.04474 (2015)"},{"key":"20_CR15","unstructured":"Gupta, S., Hariharan, B., Malik, J.: Exploring person context and local scene context for object detection. arXiv:1511.08177 (2015)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/978-3-540-88682-2_4","volume-title":"Computer Vision \u2013 ECCV 2008","author":"G Heitz","year":"2008","unstructured":"Heitz, G., Koller, D.: Learning spatial context: using stuff to find things. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 30\u201343. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_4"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Hou, R., Chen, C., Shah, M.: Tube convolutional neural network (T-CNN) for action detection in videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.620"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"20_CR21","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: NIPS (2015)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.: Towards understanding action recognition. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.B.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Action tubelet detector for spatio-temporal action localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.472"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"20_CR26","unstructured":"Kay, W., et al.: The Kinetics human action video dataset. arXiv:1705.06950 (2017)"},{"key":"20_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"20_CR28","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., et al.: 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":"20_CR29","unstructured":"Liu, W., Rabinovich, A., Berg, A.C.: Parsenet: looking wider to see better. arXiv:1506.04579 (2015)"},{"key":"20_CR30","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with restarts. In: ICLR (2017)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"20_CR34","unstructured":"Ng, J.Y., Hausknecht, M.J., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. IJCV 42(3), 145\u2013175 (2001)","DOI":"10.1023\/A:1011139631724"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"20_CR37","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-319-46493-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Xiaojiang Peng","year":"2016","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: ECCV (2016)"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Weakly-supervised learning of visual relations. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.554"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"20_CR40","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"issue":"3","key":"20_CR41","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"Olga Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. IJCV textbf115(3), 211\u2013252 (2015)","journal-title":"International Journal of Computer Vision"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Saha, S., Sing, G., Cuzzolin, F.: AMTnet: action-micro-tube regression by end-to-end trainable deep architecture. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.473"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Saha, S., Singh, G., Sapienza, M., Torr, P., Cuzzolin, F.: Deep learning for detecting multiple space-time action tubes in videos. In: BMVC (2016)","DOI":"10.5244\/C.30.58"},{"key":"20_CR44","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: NIPS (2017)"},{"key":"20_CR45","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv:1511.04119 (2015)"},{"key":"20_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/978-3-319-46448-0_20","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Shrivastava","year":"2016","unstructured":"Shrivastava, A., Gupta, A.: Contextual priming and feedback for faster R-CNN. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 330\u2013348. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_20"},{"key":"20_CR47","unstructured":"Shrivastava, A., Sukthankar, R., Malik, J., Gupta, A.: Beyond skip connections: top-down modulation for object detection. arXiv:1612.06851 (2016)"},{"key":"20_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"20_CR49","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P., Cuzzolin, F.: Online real-time multiple spatiotemporal action localisation and prediction. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.393"},{"key":"20_CR51","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"20_CR52","doi-asserted-by":"crossref","unstructured":"Torralba, A., Murphy, K.P., Freeman, W.T., Rubin, M.A.: Context-based vision system for place and object recognition. In: ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238354"},{"key":"20_CR53","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"6","key":"20_CR54","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"Gul Varol","year":"2018","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE PAMI 40(6), 1510\u20131517 (2017)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"20_CR55","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R.B., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"20_CR56","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.362"},{"key":"20_CR57","unstructured":"Weinzaepfel, P., Martin, X., Schmid, C.: Towards weakly-supervised action localization. arXiv:1605.05197 (2016)"},{"key":"20_CR58","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. In: ECCV (2018)"},{"key":"20_CR59","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3D network for temporal activity detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"20_CR60","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"20_CR61","unstructured":"Zhao, H., Yan, Z., Wang, H., Torresani, L., Torralba, A.: SLAC: a sparsely labeled dataset for action classification and localization. arXiv:1712.09374 (2017)"},{"key":"20_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"20_CR63","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NIPS (2014)"},{"key":"20_CR64","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Oliveira, G., Sedaghat, N., Brox, T.: Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.316"}],"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\/978-3-030-01252-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T01:08:37Z","timestamp":1664932117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_20","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"}]}}