{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:50:16Z","timestamp":1771959016397,"version":"3.50.1"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,9,11]],"date-time":"2018-09-11T00:00:00Z","timestamp":1536624000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2018,9,11]],"date-time":"2018-09-11T00:00:00Z","timestamp":1536624000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11263-018-1120-4","type":"journal-article","created":{"date-parts":[[2018,9,11]],"date-time":"2018-09-11T13:40:17Z","timestamp":1536673217000},"page":"263-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Pointly-Supervised Action Localization"],"prefix":"10.1007","volume":"127","author":[{"given":"Pascal","family":"Mettes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,11]]},"reference":[{"key":"1120_CR1","unstructured":"Andrews, S., Tsochantaridis., & Hofmann, T. (2002). Support vector machines for multiple-instance learning. In Advances in neural information processing systems."},{"key":"1120_CR2","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., & Fei-Fei, L. (2016). Whats the point: Semantic segmentation with point supervision. In European conference on computer vision."},{"key":"1120_CR3","doi-asserted-by":"crossref","unstructured":"Chen, W., & Corso, J. J. (2015). Action detection by implicit intentional motion clustering. In International conference on computer vision.","DOI":"10.1109\/ICCV.2015.377"},{"issue":"1","key":"1120_CR4","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TPAMI.2016.2535231","volume":"39","author":"RG Cinbis","year":"2017","unstructured":"Cinbis, R. G., Verbeek, J., & Schmid, C. (2017). Weakly supervised object localization with multi-fold multiple instance learning. IEEE transactions on pattern analysis and machine intelligence, 39(1), 189\u2013203.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"3","key":"1120_CR5","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273\u2013297.","journal-title":"Machine learning"},{"key":"1120_CR6","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., & Efros, A. A. (2015). Unsupervised visual representation learning by context prediction. In International conference on computer vision.","DOI":"10.1109\/ICCV.2015.167"},{"key":"1120_CR7","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Rabaud, V., Cottrell, G., & Belongie, S. (2005). Behavior recognition via sparse spatio-temporal features. In Visual surveillance and performance evaluation of tracking and surveillance workshops, IEEE, (pp. 65\u201372).","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"1120_CR8","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne\u00a0Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., & Darrell, T. (2015). Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1120_CR9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., & Zisserman, A. (2016). Convolutional two-stream network fusion for video action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.213"},{"key":"1120_CR10","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., & Gould, S. (2017). Self-supervised video representation learning with odd-one-out networks. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.607"},{"key":"1120_CR11","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., & Malik, J. (2015). Finding action tubes. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"1120_CR12","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Chodpathumwan, Y., & Dai, Q. (2012). Diagnosing error in object detectors. In European conference on computer vision.","DOI":"10.1007\/978-3-642-33712-3_25"},{"key":"1120_CR13","doi-asserted-by":"crossref","unstructured":"Hou, R., Chen, C., & Shah, M. (2017). Tube convolutional neural network (t-cnn) for action detection in videos. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.620"},{"key":"1120_CR14","doi-asserted-by":"crossref","unstructured":"Jain, M., Jegou, H., & Bouthemy, P. (2013). Better exploiting motion for better action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.330"},{"key":"1120_CR15","doi-asserted-by":"crossref","unstructured":"Jain, M., Van\u00a0Gemert, J., J\u00e9gou, H., Bouthemy, P., & Snoek, C. G. M. (2014). Action localization with tubelets from motion. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.100"},{"key":"1120_CR16","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J. C., Mensink, T., & Snoek, C. G. M. (2015). Objects2action: Classifying and localizing actions without any video example. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/ICCV.2015.521"},{"issue":"3","key":"1120_CR17","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s11263-017-1023-9","volume":"124","author":"M Jain","year":"2017","unstructured":"Jain, M., van Gemert, J., J\u00e9gou, H., Bouthemy, P., & Snoek, C. G. M. (2017). Tubelets: Unsupervised action proposals from spatiotemporal super-voxels. International Journal of Computer Vision, 124(3), 287\u2013311.","journal-title":"International Journal of Computer Vision"},{"key":"1120_CR18","unstructured":"Jain, S. D., & Grauman, K. (2016). Click carving: Segmenting objects in video with point clicks. arXiv preprint \n                    arXiv:1607.01115\n                    \n                  ."},{"issue":"1","key":"1120_CR19","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. (2013). 3d convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, 35(1), 221\u2013231.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"1120_CR20","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., & Schmid, C. (2017a). Action tubelet detector for spatio-temporal action localization. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.472"},{"key":"1120_CR21","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., & Schmid, C. (2017b). Joint learning of object and action detectors. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.219"},{"key":"1120_CR22","unstructured":"Lan, T., Wang, Y., & Mori, G. (2011). Discriminative figure-centric models for joint action localization and recognition. In International conference on computer vision."},{"issue":"2\u20133","key":"1120_CR23","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I. (2005). On space-time interest points. International Journal of Computer Vision, 64(2\u20133), 107\u2013123.","journal-title":"International Journal of Computer Vision"},{"key":"1120_CR24","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., & Snoek, C. G. M. (2018). Videolstm convolves, attends and flows for action recognition. Computer Vision and Image Understanding, 166, 41\u201350.","journal-title":"Computer Vision and Image Understanding"},{"key":"1120_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1120_CR26","doi-asserted-by":"crossref","unstructured":"Manen, S., Gygli, M., Dai, D., & Van\u00a0Gool, L. (2017). Pathtrack: Fast trajectory annotation with path supervision. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.40"},{"key":"1120_CR27","unstructured":"Marian\u00a0Puscas, M., Sangineto, E., Culibrk, D., & Sebe, N. (2015). Unsupervised tube extraction using transductive learning and dense trajectories. In International conference on computer vision."},{"key":"1120_CR28","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., Laptev, I., & Schmid, C. (2009). Actions in context. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"1120_CR29","doi-asserted-by":"crossref","unstructured":"Mettes, P., & Snoek, C. G. M. (2017). Spatial-aware object embeddings for zero-shot localization and classification of actions. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.476"},{"key":"1120_CR30","doi-asserted-by":"crossref","unstructured":"Mettes, P., van Gemert, J. C., & Snoek, C. G. M. (2016). Spot on: Action localization from pointly-supervised proposals. In European conference on computer vision.","DOI":"10.1007\/978-3-319-46454-1_27"},{"key":"1120_CR31","doi-asserted-by":"crossref","unstructured":"Mettes, P., Snoek, C. G. M., & Chang, S. F. (2017). Localizing actions from video labels and pseudo-annotations. In British machine vision conference.","DOI":"10.5244\/C.31.22"},{"key":"1120_CR32","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In Workshops at the twenty-sixth AAAI conference on artificial intelligence."},{"key":"1120_CR33","doi-asserted-by":"crossref","unstructured":"Oneata, D., Revaud, J., Verbeek, J., & Schmid, C. (2014). Spatio-temporal object detection proposals. In European conference on computer vision.","DOI":"10.1007\/978-3-319-10578-9_48"},{"key":"1120_CR34","doi-asserted-by":"crossref","unstructured":"Papadopoulos, D. P., Uijlings, J. R., Keller, F., & Ferrari, V. (2016). We don\u2019t need no bounding-boxes: Training object class detectors using only human verification. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.99"},{"key":"1120_CR35","doi-asserted-by":"crossref","unstructured":"Papadopoulos, D. P., Uijlings, J. R., Keller, F., & Ferrari, V. (2017). Extreme clicking for efficient object annotation. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.528"},{"key":"1120_CR36","doi-asserted-by":"crossref","unstructured":"Peng, X., & Schmid, C. (2016). Multi-region two-stream r-cnn for action detection. In European conference on computer vision.","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"1120_CR37","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems."},{"key":"1120_CR38","doi-asserted-by":"crossref","unstructured":"Rodriguez, M. D., Ahmed, J., & Shah, M. (2008). Action MACH: a spatio-temporal maximum average correlation height filter for action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"1120_CR39","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Li, L. J., & Fei-Fei, L. (2015). Best of both worlds: human-machine collaboration for object annotation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298824"},{"key":"1120_CR40","doi-asserted-by":"crossref","unstructured":"Saha, S., Singh, G., Sapienza, M., Torr, P., & Cuzzolin, F. (2016). Deep learning for detecting multiple space-time action tubes in videos. In British machine vision conference.","DOI":"10.5244\/C.30.58"},{"key":"1120_CR41","doi-asserted-by":"crossref","unstructured":"Saha, S., Singh, G., & Cuzzolin, F. (2017). Amtnet: Action-micro-tube regression by end-to-end trainable deep architecture. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.473"},{"issue":"3","key":"1120_CR42","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez, J., Perronnin, F., Mensink, T., & Verbeek, J. (2013). Image classification with the fisher vector: Theory and practice. International Journal of Computer Vision, 105(3), 222\u2013245.","journal-title":"International Journal of Computer Vision"},{"key":"1120_CR43","unstructured":"Sharma, S., Kiros, R., & Salakhutdinov, R. (2015). Action recognition using visual attention. In Advances in neural information processing systems workshop."},{"key":"1120_CR44","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems."},{"key":"1120_CR45","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P., & Cuzzolin, F. (2017). Online real-time multiple spatiotemporal action localisation and prediction. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.393"},{"key":"1120_CR46","doi-asserted-by":"crossref","unstructured":"Siva, P., Xiang, T. (2011). Weakly supervised action detection. In British machine vision conference.","DOI":"10.5244\/C.25.65"},{"key":"1120_CR47","doi-asserted-by":"crossref","unstructured":"Soomro, K., & Shah, M. (2017). Unsupervised action discovery and localization in videos. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.82"},{"key":"1120_CR48","unstructured":"Soomro, K., Zamir, A. R., & Shah, M.(2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint \n                    arXiv:12120402\n                    \n                  ."},{"key":"1120_CR49","doi-asserted-by":"crossref","unstructured":"Soomro, K., Idrees, H., & Shah, M. (2015). Action localization in videos through context walk. In International conference on computer vision.","DOI":"10.1109\/ICCV.2015.375"},{"key":"1120_CR50","unstructured":"Srivastava, N., Mansimov, E., & Salakhudinov, R. (2015). Unsupervised learning of video representations using lstms. In International conference on machine learning."},{"key":"1120_CR51","unstructured":"Su, H., Deng, J., & Fei-Fei, L. (2012). Crowdsourcing annotations for visual object detection. In AAAI workshops."},{"key":"1120_CR52","doi-asserted-by":"crossref","unstructured":"Tian, Y., Sukthankar, R., & Shah, M. (2013a). Spatiotemporal deformable part models for action detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.341"},{"key":"1120_CR53","doi-asserted-by":"crossref","unstructured":"Tian, Y., Sukthankar, R., & Shah, M. (2013b). Spatiotemporal deformable part models for action detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.341"},{"key":"1120_CR54","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. In International conference on computer vision.","DOI":"10.1109\/ICCV.2015.510"},{"issue":"7","key":"1120_CR55","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/9.7.4","volume":"9","author":"PH Tseng","year":"2009","unstructured":"Tseng, P. H., Carmi, R., Cameron, I. G., Munoz, D. P., & Itti, L. (2009). Quantifying center bias of observers in free viewing of dynamic natural scenes. Journal of Vision, 9(7), 4.","journal-title":"Journal of Vision"},{"issue":"2","key":"1120_CR56","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J. R. R., Van De Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013). Selective search for object recognition. International Journal of Computer Vision, 104(2), 154\u2013171.","journal-title":"International Journal of Computer Vision"},{"key":"1120_CR57","doi-asserted-by":"crossref","unstructured":"van Gemert, J. C., Jain, M., Gati, E., & Snoek, C. G. M. (2015). Apt: Action localization proposals from dense trajectories. In British machine vision conference.","DOI":"10.5244\/C.29.177"},{"issue":"1","key":"1120_CR58","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/s11263-012-0564-1","volume":"101","author":"C Vondrick","year":"2013","unstructured":"Vondrick, C., Patterson, D., & Ramanan, D. (2013). Efficiently scaling up crowdsourced video annotation. International Journal of Computer Vision, 101(1), 184\u2013204.","journal-title":"International Journal of Computer Vision"},{"key":"1120_CR59","doi-asserted-by":"crossref","unstructured":"Wang, H., & Schmid, C. (2013). Action recognition with improved trajectories. In International conference on computer vision.","DOI":"10.1109\/ICCV.2013.441"},{"key":"1120_CR60","doi-asserted-by":"crossref","unstructured":"Wang, H., Ullah, M. M., Klaser, A., Laptev, I., & Schmid, C. (2009). Evaluation of local spatio-temporal features for action recognition. In British machine vision conference.","DOI":"10.5244\/C.23.124"},{"issue":"1","key":"1120_CR61","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., & Liu, C. L. (2013). Dense trajectories and motion boundary descriptors for action recognition. International Journal of Computer Vision, 103(1), 60\u201379.","journal-title":"International Journal of Computer Vision"},{"key":"1120_CR62","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., & Tang, X. (2014). Video action detection with relational dynamic-poselets. In European conference on computer vision.","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"1120_CR63","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., & Schmid, C. (2015). Learning to track for spatio-temporal action localization. In International conference on computer vision.","DOI":"10.1109\/ICCV.2015.362"},{"key":"1120_CR64","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, J., & Nevatia, R. (2017). Spatio-temporal action detection with cascade proposal and location anticipation. In British machine vision conference.","DOI":"10.5244\/C.31.95"},{"key":"1120_CR65","doi-asserted-by":"crossref","unstructured":"Yu, G., & Yuan, J. (2015). Fast action proposals for human action detection and search. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298735"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-018-1120-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1120-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1120-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T07:23:22Z","timestamp":1589700202000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-018-1120-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,11]]},"references-count":65,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["1120"],"URL":"https:\/\/doi.org\/10.1007\/s11263-018-1120-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,11]]},"assertion":[{"value":"29 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}