{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T16:00:54Z","timestamp":1792944054208,"version":"4.5.0"},"publisher-location":"Cham","reference-count":93,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012274","type":"print"},{"value":"9783030012281","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\/978-3-030-01228-1_25","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T05:03:51Z","timestamp":1538802231000},"page":"413-431","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":455,"title":["Videos as Space-Time Region Graphs"],"prefix":"10.1007","author":[{"given":"Xiaolong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"25_CR1","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Neural Information Processing Systems (NIPS) (2014)"},{"key":"25_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"25_CR5","unstructured":"Li, F., et al.: Temporal modeling approaches for large-scale Youtube-8M video understanding. arXiv preprint arXiv:1707.04555 (2017)"},{"key":"25_CR6","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learnable pooling with context gating for video classification. arXiv preprint arXiv:1706.06905 (2017)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"25_CR9","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"25_CR10","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv:1712.04851 (2017)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Russakovsky, O., Gupta, A.: What actions are needed for understanding human actions in videos? In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.235"},{"key":"25_CR12","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: using spatial and functional compatibility for recognition. Trans. Pattern Anal. Mach. Intell. (TPAMI) 31, 1775\u20131789 (2009)","journal-title":"Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: Computer Vision and Pattern Recognition (CVPR) (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Yatskar, M., Zettlemoyer, L., Farhadi, A.: Situation recognition: visual semantic role labeling for image understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.597"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"25_CR16","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":"25_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with R*CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.129"},{"key":"25_CR19","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"25_CR20","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":"25_CR21","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. arXiv:1706.04261 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. IJCV 64, 107\u2013123 (2005)","journal-title":"IJCV"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: BMVC (2008)","DOI":"10.5244\/C.22.99"},{"key":"25_CR25","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":"25_CR26","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.J.: Action bank: a high-level representation of activity in video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"25_CR28","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TPAMI.2010.214","volume":"33","author":"Y Wang","year":"2011","unstructured":"Wang, Y., Mori, G.: Hidden part models for human action recognition: probabilistic vs. max-margin. TPAMI 33, 1310\u20131323 (2011)","journal-title":"TPAMI"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, J., Wang, B., Yang, X., Zhang, W., Tu, Z.: Action recognition with actons. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.442"},{"key":"25_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-319-10602-1_38","volume-title":"Computer Vision \u2013 ECCV 2014","author":"X Peng","year":"2014","unstructured":"Peng, X., Zou, C., Qiao, Y., Peng, Q.: Action recognition with stacked fisher vectors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 581\u2013595. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_38"},{"key":"25_CR31","unstructured":"Lan, Z., Lin, M., Li, X., Hauptmann, A.G., Raj, B.: Beyond Gaussian pyramid: multi-skip feature stacking for action recognition. In: CVPR (2015)"},{"key":"25_CR32","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":"25_CR33","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"25_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-642-15567-3_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"GW Taylor","year":"2010","unstructured":"Taylor, G.W., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 140\u2013153. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15567-3_11"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Torralba, A.: Temporal relational reasoning in videos (2017)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Farhadi, A., Gupta, A.: Actions transformations. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.291"},{"key":"25_CR38","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. arXiv:1502.04681 (2015)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Sun, C., Shetty, S., Sukthankar, R., Nevatia, R.: Temporal localization of fine-grained actions in videos by domain transfer from web images. In: ACM Multimedia (2015)","DOI":"10.1145\/2733373.2806226"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, X., Jiang, Y.G., Ye, H., Xue, X.: Modeling spatial-temporal clues in a hybrid deep learning framework for video classification. arXiv:1504.01561 (2015)","DOI":"10.1145\/2733373.2806222"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Gan, C., Yao, T., Yang, K., Yang, Y., Mei, T.: You lead, we exceed: labor-free video concept learning by jointly exploiting web videos and images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.106"},{"key":"25_CR42","unstructured":"Bian, Y., et al.: Revisiting the effectiveness of off-the-shelf temporal modeling approaches for large-scale video classification. arXiv:1708.03805 (2017)"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Pan, P., Xu, Z., Yang, Y., Wu, F., Zhuang, Y.: Hierarchical recurrent neural encoder for video representation with application to captioning. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.117"},{"key":"25_CR44","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. TPAMI 35, 221\u2013231 (2013)","journal-title":"TPAMI"},{"key":"25_CR45","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"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Neural Information Processing Systems (NIPS) (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"25_CR49","unstructured":"Yao, J., Fidler, S., Urtasun, R.: Describing the scene as a whole: joint object detection, scene classification and semantic segmentation. In: CVPR (2012)"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Kumar, M.P., Koller, D.: Efficiently selecting regions for scene understanding. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540072"},{"key":"25_CR51","unstructured":"Russell, B.C., Freeman, W.T., Efros, A.A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)"},{"key":"25_CR52","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Neural Information Processing Systems (NIPS) (2017)"},{"key":"25_CR53","unstructured":"Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Neural Information Processing Systems (NIPS) (2016)"},{"key":"25_CR54","unstructured":"Watters, N., Tacchetti, A., Weber, T., Pascanu, R., Battaglia, P., Zoran, D.: Visual interaction networks. In: Neural Information Processing Systems (NIPS) (2017)"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Ma, C.Y., Kadav, A., Melvin, I., Kira, Z., AlRegib, G., Graf, H.P.: Attend and interact: higher-order object interactions for video understanding. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00710"},{"key":"25_CR56","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Actions and attributes from wholes and parts. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.284"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Ni, B., Yang, X., Gao, S.: Progressively parsing interactional objects for fine grained action detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.116"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"25_CR59","unstructured":"Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning (ICML) (2001)"},{"key":"25_CR60","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Neural Information Processing Systems (NIPS) (2011)"},{"key":"25_CR61","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv:1412.7062 (2014)"},{"key":"25_CR62","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Chandra, S., Usunier, N., Kokkinos, I.: Dense and low-rank Gaussian CRFs using deep embeddings. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.546"},{"key":"25_CR64","unstructured":"Schwing, A.G., Urtasun, R.: Fully connected deep structured networks. arXiv preprint arXiv:1503.02351 (2015)"},{"key":"25_CR65","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: NIPS (2011)"},{"key":"25_CR66","doi-asserted-by":"crossref","unstructured":"Harley, A., Derpanis, K., Kokkinos, I.: Segmentation-aware convolutional networks using local attention masks. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.539"},{"key":"25_CR67","unstructured":"Liu, S., De Mello, S., Gu, J., Zhong, G., Yang, M.H., Kautz, J.: Learning affinity via spatial propagation networks. In: Neural Information Processing Systems (NIPS) (2017)"},{"key":"25_CR68","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20, 61\u201380 (2009)","journal-title":"IEEE Trans. Neural Netw."},{"key":"25_CR69","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. In: ICLR (2016)"},{"key":"25_CR70","doi-asserted-by":"crossref","unstructured":"Marino, K., Salakhutdinov, R., Gupta, A.: The more you know: using knowledge graphs for image classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.10"},{"key":"25_CR71","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"25_CR72","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Sivic, J., Laptev, I., Lacoste-Julien, S.: Joint discovery of object states and manipulation actions. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.234"},{"key":"25_CR73","doi-asserted-by":"crossref","unstructured":"Wu, Z., Fu, Y., Jiang, Y.G., Sigal, L.: Harnessing object and scene semantics for large-scale video understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.339"},{"key":"25_CR74","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Barrios, W., Escorcia, V., Ghanem, B.: SCC: semantic context cascade for efficient action detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.338"},{"key":"25_CR75","doi-asserted-by":"crossref","unstructured":"Brendel, W., Todorovic, S.: Learning spatiotemporal graphs of human activities. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"25_CR76","unstructured":"Chen, C.Y., Grauman, K.: Efficient activity detection with max-subgraph search. In: CVPR (2012)"},{"key":"25_CR77","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"25_CR78","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Liang, X., Wang, X., Yeung, D.Y., Gupta, A.: Temporal dynamic graph LSTM for action-driven video object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.200"},{"key":"25_CR79","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Neural Information Processing Systems (NIPS) (2015)"},{"key":"25_CR80","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"25_CR81","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"25_CR82","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron"},{"key":"25_CR83","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"25_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR85","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (NIPS) (2017)"},{"key":"25_CR86","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"25_CR87","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. Vis. (IJCV) 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"25_CR88","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv:1705.06950 (2017)"},{"key":"25_CR89","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"25_CR90","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580 (2012)"},{"key":"25_CR91","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imageNet in 1 hour. arXiv:1706.02677 (2017)"},{"key":"25_CR92","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1214\/ss\/1177012582","volume":"4","author":"DG Kendall","year":"1989","unstructured":"Kendall, D.G.: A survey of the statistical theory of shape. Stat. Sci. 4, 87\u201399 (1989)","journal-title":"Stat. Sci."},{"key":"25_CR93","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Divvala, S., Farhadi, A., Gupta, A.: Asynchronous temporal fields for action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.599"}],"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\/978-3-030-01228-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:30:21Z","timestamp":1665016221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":93,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25","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"}]}}