{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T14:56:25Z","timestamp":1780584985519,"version":"3.54.1"},"reference-count":90,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,8,10]],"date-time":"2016-08-10T00:00:00Z","timestamp":1470787200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","award":["Faculty Research Award Summer 2014"],"award-info":[{"award-number":["Faculty Research Award Summer 2014"]}],"id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["Starting Grant VisCul 308003"],"award-info":[{"award-number":["Starting Grant VisCul 308003"]}],"id":[{"id":"10.13039\/501100000781","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":[[2017,1]]},"DOI":"10.1007\/s11263-016-0939-9","type":"journal-article","created":{"date-parts":[[2016,8,9]],"date-time":"2016-08-09T21:57:36Z","timestamp":1470779856000},"page":"303-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Behavior Discovery and Alignment of Articulated Object Classes from Unstructured Video"],"prefix":"10.1007","volume":"121","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3795-0689","authenticated-orcid":false,"given":"Luca","family":"Del Pero","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susanna","family":"Ricco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Sukthankar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vittorio","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,8,10]]},"reference":[{"key":"939_CR1","doi-asserted-by":"crossref","unstructured":"Azizpour, H., & Laptev, I. (2012). Object detection using strongly-supervised deformable part models. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-33718-5_60"},{"key":"939_CR2","doi-asserted-by":"crossref","unstructured":"Barnes, C., Shechtman, E., Goldman, D., & Finkelstein, A. (2010). The generalized patchmatch correspondence algorithm. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-15558-1_3"},{"key":"939_CR3","doi-asserted-by":"crossref","unstructured":"Bourdev, L., & Malik, J. (2009). Poselets: Body part detectors trained using 3D human pose annotations. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2009.5459303"},{"issue":"1","key":"939_CR4","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s11263-006-0002-3","volume":"74","author":"M Brown","year":"2007","unstructured":"Brown, M., & Lowe, D. (2007). Automatic panoramic image stitching using invariant features. Journal of Computer Vision, 74(1), 59\u201373.","journal-title":"Journal of Computer Vision"},{"issue":"3","key":"939_CR5","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","volume":"33","author":"T Brox","year":"2011","unstructured":"Brox, T., & Malik, J. (2011). Large displacement optical flow: Descriptor matching in variational motion estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3), 500\u2013513.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"939_CR6","doi-asserted-by":"crossref","unstructured":"Caspi, Y., & Irani, M. (2000). A step towards sequence-to-sequence alignment. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2000.854940"},{"issue":"1","key":"939_CR7","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s11263-005-4842-z","volume":"68","author":"Y Caspi","year":"2006","unstructured":"Caspi, Y., Simakov, D., & Irani, M. (2006). Feature-based sequence-to-sequence matching. International Journal of Computer Vision, 68(1), 53\u201364.","journal-title":"International Journal of Computer Vision"},{"issue":"2\u20133","key":"939_CR8","first-page":"114","volume":"89","author":"H Chui","year":"2003","unstructured":"Chui, H., & Rangarajan, A. (2003). A new point matching algorithm for non-rigid registration. CVIU, 89(2\u20133), 114\u2013141.","journal-title":"CVIU"},{"key":"939_CR9","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1109\/TPAMI.2007.70787","volume":"30","author":"O Chum","year":"2008","unstructured":"Chum, O., & Matas, J. (2008). Optimal randomized RANSAC. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 1472\u20131482.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"939_CR10","doi-asserted-by":"crossref","unstructured":"Cinbis, R., Verbeek, J., & Schmid, C. (2013). Segmentation driven object detection with Fisher vectors. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2013.369"},{"key":"939_CR11","doi-asserted-by":"crossref","unstructured":"Cootes, T., Edwards, G., & Taylor, C. (1998). Active appearance models. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/BFb0054760"},{"key":"939_CR12","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histogram of oriented gradients for human detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2005.177"},{"key":"939_CR13","doi-asserted-by":"crossref","unstructured":"Del Pero, L., Ricco, S., Sukthankar, R., & Ferrari, V. (2015a). Articulated motion discovery using pairs of trajectories. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298827"},{"key":"939_CR14","doi-asserted-by":"crossref","unstructured":"Del Pero, L., Ricco, S., Sukthankar, R., & Ferrari, V. (2015b). Dataset for articulated motion discovery using pairs of trajectories. http:\/\/www.groups.inf.ed.ac.uk\/calvin\/proj-pots\/page\/ .","DOI":"10.1109\/CVPR.2015.7298827"},{"key":"939_CR15","doi-asserted-by":"crossref","unstructured":"Dexter, E., Perez, P., & Laptev, I. (2009). Multi-view synchronization of human actions and dynamic scenes. In Proceedings of the British machine vision conference.","DOI":"10.5244\/C.23.122"},{"key":"939_CR16","doi-asserted-by":"crossref","unstructured":"Dollar, P., & Zitnick, C. (2013). Structured forests for fast edge detection. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2013.231"},{"key":"939_CR17","unstructured":"Douze, M., Revaud, J., Verbeek, J., Jegou, H., & Schmid, C. (2015). Circulant temporal encoding for video retrieval and temporal alignment. arXiv:1506.02588v1 ."},{"key":"939_CR18","doi-asserted-by":"crossref","first-page":"2371","DOI":"10.1109\/TPAMI.2013.56","volume":"35","author":"GD Evangelidis","year":"2013","unstructured":"Evangelidis, G. D., & Bauckhage, C. (2013). Efficient subframe video alignment using short descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 2371\u20132386.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"8","key":"939_CR19","doi-asserted-by":"crossref","first-page":"2315","DOI":"10.1109\/TIP.2011.2109727","volume":"20","author":"Q Fan","year":"2011","unstructured":"Fan, Q., Barnard, K., Amir, A., & Efrat, A. (2011). Robust spatio-temporal matching of electronic slides to presentation videos. IEEE Transactions on Image Processing, 20(8), 2315\u20132328.","journal-title":"IEEE Transactions on Image Processing"},{"key":"939_CR20","first-page":"59","volume":"106","author":"L Fei-Fei","year":"2007","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2007). Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. CVIU, 106, 59\u201370.","journal-title":"CVIU"},{"issue":"9","key":"939_CR21","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"P Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P., Girshick, R., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9), 1627\u20131645.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"939_CR22","first-page":"55","volume":"61","author":"P Felzenszwalb","year":"2005","unstructured":"Felzenszwalb, P., & Huttenlocher, D. (2005). Pictorial structures for object recognition. IJCV, 61(1), 55\u201379.","journal-title":"Pictorial structures for object recognition. IJCV"},{"issue":"3","key":"939_CR23","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1007\/s11263-009-0270-9","volume":"87","author":"V Ferrari","year":"2010","unstructured":"Ferrari, V., Jurie, F., & Schmid, C. (2010). From images to shape models for object detection. International Journal of Computer Vision, 87(3), 284\u2013303.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"939_CR24","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s11263-005-3964-7","volume":"67","author":"V Ferrari","year":"2006","unstructured":"Ferrari, V., Tuytelaars, T., & Van Gool, L. (2006). Simultaneous object recognition and segmentation from single or multiple model views. International Journal of Computer Vision, 67(2), 159\u2013188.","journal-title":"International Journal of Computer Vision"},{"issue":"6","key":"939_CR25","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the Association for Computer Machinery, 24(6), 381\u2013395.","journal-title":"Communications of the Association for Computer Machinery"},{"key":"939_CR26","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.81"},{"issue":"12","key":"939_CR27","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick, L., Blank, M., Shechtman, E., Irani, M., & Basri, R. (2007). Actions as space-time shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(12), 2247\u20132253.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"939_CR28","volume-title":"Multiple view geometry in computer vision","author":"RI Hartley","year":"2000","unstructured":"Hartley, R. I., & Zisserman, A. (2000). Multiple view geometry in computer vision. Cambridge: Cambridge University Press."},{"key":"939_CR29","doi-asserted-by":"crossref","unstructured":"Hospedales, T., Gong, S., & Xiang, T. (2009). A Markov clustering topic model for mining behaviour in video. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2009.5459342"},{"issue":"9","key":"939_CR30","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1109\/TPAMI.2006.176","volume":"28","author":"W Hu","year":"2006","unstructured":"Hu, W., Xiao, X., Fu, Z., Xie, D., Tan, T., & Maybank, S. (2006). A system for learning statistical motion patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(9), 1450\u20131464.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"939_CR31","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF01908075","volume":"2","author":"L Hubert","year":"1985","unstructured":"Hubert, L., & Arabie, P. (1985). Comparing partitions. Journal of Classification, 2(1), 193\u2013218.","journal-title":"Journal of Classification"},{"key":"939_CR32","doi-asserted-by":"crossref","unstructured":"Jain, A., Gupta, A., Rodriguez, M., & Davis, L. (2013). Representing videos using mid-level discriminative patches. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.332"},{"key":"939_CR33","doi-asserted-by":"crossref","unstructured":"Jegou, H., Douze, M., & Schmid, C. (2008). Hamming embedding and weak geometric consistency for large-scale image search. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-540-88682-2_24"},{"key":"939_CR34","doi-asserted-by":"crossref","unstructured":"Jiang, Y. G., Dai, Q., Xue, X., Liu, W., & Ngo, C. W. (2012). Trajectory-based modeling of human actions with motion reference points. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-33715-4_31"},{"key":"939_CR35","unstructured":"Jiang, Y. G., Liu, J., Toderici, G., Zamir, A. R., Laptev, I., Shah, M., & Sukthankar, R. (2014). THUMOS: ECCV workshop on action recognition with a large number of classes."},{"key":"939_CR36","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/BF02289588","volume":"2","author":"SC Johnson","year":"1967","unstructured":"Johnson, S. C. (1967). Hierarchical clustering schemes. Psychometrika, 2, 241\u2013254.","journal-title":"Psychometrika"},{"key":"939_CR37","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.223"},{"key":"939_CR38","doi-asserted-by":"crossref","unstructured":"Ke, Y., Sukthankar, R., & Hebert, M. (2007). Event detection in crowded videos. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"939_CR39","unstructured":"Kim, W. H., & Kim, J. N. (2009). An adaptive shot change detection algorithm using an average of absolute difference histogram within extension sliding window. In International symposium on consumer electronics."},{"key":"939_CR40","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). HMDB: A large video database for human motion recognition. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"939_CR41","doi-asserted-by":"crossref","unstructured":"Kuettel, D., Breitenstein, M., van Gool, L., & Ferrari, V. (2010). What\u2019s going on? Discovering spatio-temporal dependencies in dynamic scenes. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2010.5539869"},{"key":"939_CR42","unstructured":"Kuettel, D., Guillaumin, M., & Ferrari, V. (2012). Segmentation propagation in ImageNet. In Proceedings of the European conference on computer vision. http:\/\/www.groups.inf.ed.ac.uk\/calvin\/Publications\/kuettelECCV12.pdf ."},{"key":"939_CR43","doi-asserted-by":"crossref","unstructured":"Lampert, C., Nickisch, H., & Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"939_CR44","doi-asserted-by":"crossref","unstructured":"Leistner, C., Godec, M., Schulter, S., Saffari, A., & Bischof, H. (2011). Improving classifiers with weakly-related videos. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995475"},{"key":"939_CR45","doi-asserted-by":"crossref","unstructured":"Leordeanu, M., Hebert, M., & Sukthankar, R. (2007). Beyond local appearance: Category recognition from pairwise interactions of simple features. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2007.383091"},{"key":"939_CR46","doi-asserted-by":"crossref","unstructured":"Liao, J., Lima, R. S., Nehab, D., Hoppe, H., & Sander, P. V. (2014). Semi-automated video morphing. In Eurographics symposium on rendering.","DOI":"10.1111\/cgf.12412"},{"key":"939_CR47","doi-asserted-by":"crossref","unstructured":"Liu, C., Yuen, J., Torralba, A., Sivic, J., & Freeman, W. (2008). SIFT flow: Dense correspondence across different scenes. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-540-88690-7_3"},{"issue":"2","key":"939_CR48","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe, D. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"939_CR49","doi-asserted-by":"crossref","unstructured":"Mahadevan, V., Li, W., Bhalodia, V., & Vasconcelos, N. (2010). Anomaly detection in crowded scenes. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"939_CR50","doi-asserted-by":"crossref","unstructured":"Malisiewicz, T., Gupta, A., & Efros, A. (2011). Ensemble of exemplar-SVMs for object detection and beyond. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"939_CR51","doi-asserted-by":"crossref","unstructured":"Martin, D., Fowlkes, D., Tal, D., & Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2001.937655"},{"key":"939_CR52","unstructured":"Matikainen, P., Hebert, M., & Sukthankar, R. (2009). Trajections: Action recognition through the motion analysis of tracked features. In ICCV workshop on video-oriented object and event classification."},{"key":"939_CR53","doi-asserted-by":"crossref","unstructured":"Matikainen, P., Hebert, M., & Sukthankar, R. (2010). Representing pairwise spatial and temporal relations for action recognition. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-15549-9_37"},{"key":"939_CR54","doi-asserted-by":"crossref","unstructured":"Messing, R., Pal, C., & Kautz, H. (2009). Activity recognition using the velocity histories of tracked keypoints. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"939_CR55","doi-asserted-by":"crossref","unstructured":"Narayan, S., & Ramakrishnan, K. R. (2014). A cause and effect analysis of motion trajectories for modeling actions. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.337"},{"key":"939_CR56","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., & Ferrari, V. (2013). Fast object segmentation in unconstrained video. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2013.223"},{"key":"939_CR57","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistner, C., Civera, J., Schmid, C., & Ferrari, V. (2012). Learning object class detectors from weakly annotated video. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2012.6248065"},{"issue":"8","key":"939_CR58","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1109\/TPAMI.2006.155","volume":"28","author":"D Ramanan","year":"2006","unstructured":"Ramanan, D., Forsyth, A., & Barnard, K. (2006). Building models of animals from video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(8), 1319\u20131334.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"939_CR59","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","volume":"66","author":"WM Rand","year":"1971","unstructured":"Rand, W. M. (1971). Objective criteria for the evaluation of clustering methods. Journal of the American Statistical Association, 66, 846\u2013850.","journal-title":"Journal of the American Statistical Association"},{"key":"939_CR60","doi-asserted-by":"crossref","unstructured":"Rao, C., Gritai, A., & Shah, M. (2003). View-invariant alignment and matching of video sequences. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2003.1238449"},{"key":"939_CR61","doi-asserted-by":"crossref","unstructured":"Raptis, M., Kokkinos, I., & Soatto, S. (2012). Discovering discriminative action parts from mid-level video representations. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"939_CR62","doi-asserted-by":"crossref","unstructured":"Raptis, M., & Soatto, S. (2010). Tracklet descriptors for action modeling and video analysis. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-15549-9_42"},{"key":"939_CR63","doi-asserted-by":"crossref","unstructured":"Ryoo, M. S., & Aggarwal, J. K. (2009). Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"939_CR64","doi-asserted-by":"crossref","unstructured":"Santos, J. M., & Embrechts, M. (2009). On the use of the adjusted rand index as a metric for evaluating supervised classification. In Proceedings of the 19th international conference on artificial neural networks, Limassol, Cyprus.","DOI":"10.1007\/978-3-642-04277-5_18"},{"key":"939_CR65","volume-title":"Combining grey value invariants with local constraints for object recognition. Technical report","author":"C Schmid","year":"1996","unstructured":"Schmid, C., & Mohr, R. (1996). Combining grey value invariants with local constraints for object recognition. Technical report. Grenoble: INRIA."},{"key":"939_CR66","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., & Caputo, B. (2004). Recognizing human actions: A local SVM approach. In Proceedings of the international conference on pattern recognition.","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"939_CR67","doi-asserted-by":"crossref","unstructured":"Seitz, S., Curless, B., Diebel, J., Scharstein, D., & Szeliski, R. (2006). A comparison and evaluation of multi-view stereo reconstruction algorithms. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2006.19"},{"key":"939_CR68","doi-asserted-by":"crossref","DOI":"10.1145\/1178677.1178722","volume-title":"Evaluation campaigns and TRECVID","author":"AF Smeaton","year":"2006","unstructured":"Smeaton, A. F., Over, P., & Kraaij, W. (2006). Evaluation campaigns and TRECVID. New York, NY, USA: In ACM international workshop on multimedia information retrieval."},{"key":"939_CR69","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). UCF101: A dataset of 101 human action classes from videos in the wild. Technical report CRCV-TR-12-01. University of Central Florida."},{"key":"939_CR70","doi-asserted-by":"crossref","unstructured":"Tang, K., Sukthankar, R., Yagnik, J., & Fei-Fei, L. (2013). Discriminative segment annotation in weakly labeled video. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.321"},{"key":"939_CR71","doi-asserted-by":"crossref","unstructured":"Tighe, J., & Lazebnik, S. (2013). Finding things: Image parsing with regions and per-exemplar detectors. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.386"},{"key":"939_CR72","doi-asserted-by":"crossref","unstructured":"Tompkin, J., Kim, K. I., Kautz, J., & Theobalt, C. (2012). Videoscapes: Exploring sparse, unstructured video collections. In Proceedings of the ACM SIGGRAPH conference on computer graphics.","DOI":"10.1145\/2185520.2185564"},{"key":"939_CR73","doi-asserted-by":"crossref","unstructured":"Tuytelaars, T., & van Gool, L. (2004). Synchronizing video sequences. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2004.1315108"},{"key":"939_CR74","doi-asserted-by":"crossref","unstructured":"Ukrainitz, Y., & Irani, M. (2006). Aligning sequences and actions by maximizing space\u2013time correlations. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/11744078_42"},{"key":"939_CR75","doi-asserted-by":"crossref","unstructured":"Vezhnevets, A., & Ferrari, V. (2014). Associative embeddings for large-scale knowledge transfer with self-assessment. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.255"},{"key":"939_CR76","unstructured":"Viola, P. A., Platt, J., & Zhang, C. (2005). Multiple instance boosting for object detection. In Advances in neural information processing systems."},{"key":"939_CR77","doi-asserted-by":"crossref","unstructured":"Wahba, G. (1990). Spline models for observational data. In CBMS-NSF regional conference series in applied mathematics (Vol. 59). Philadelphia: SIAM.","DOI":"10.1137\/1.9781611970128"},{"key":"939_CR78","unstructured":"Wan, F., & M\u00e9rialdo, B. (2009). Multi-document video summarization. In Proceedings of the 2009 IEEE international conference on multimedia and expo."},{"key":"939_CR79","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., & Cheng-Lin, L. (2011). Action recognition by dense trajectories. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"939_CR80","doi-asserted-by":"crossref","unstructured":"Wang, H., & Schmid, C. (2013). Action recognition with improved trajectories. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2013.441"},{"key":"939_CR81","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., & Tang, X. (2014). Video action detection with relational dynamic-poselets. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"939_CR82","first-page":"1","volume":"33","author":"O Wang","year":"2014","unstructured":"Wang, O., Schroers, C., Zimmer, H., Gross, M., & Sorkine-Hornung, A. (2014). Videosnapping: Interactive synchronization of multiple videos. ACM Transactions on Graphics, 33, 1\u201310.","journal-title":"ACM Transactions on Graphics"},{"issue":"3","key":"939_CR83","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TPAMI.2008.87","volume":"31","author":"X Wang","year":"2009","unstructured":"Wang, X., Ma, X., & Grimson, W. (2009). Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(3), 539\u2013555.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"939_CR84","doi-asserted-by":"crossref","unstructured":"Wang, X., Yang, M., Zhu, S., & Lin, Y. (2013). Regionlets for generic object detection. In Proceedings of the international conference on computer vision (pp. 17\u201324). IEEE.","DOI":"10.1109\/ICCV.2013.10"},{"key":"939_CR85","unstructured":"Yang, S., Chen, M., Pomerleau, D., & Sukthankar, R. (2010). Food recognition using statistics of pairwise local features. In Proceedings of the IEEE conference on computer vision and pattern recognition."},{"issue":"12","key":"939_CR86","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang, Y., & Ramanan, D. (2013). Articulated human detection with flexible mixtures-of-parts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(12), 2878\u20132890.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"939_CR87","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1109\/TPAMI.2012.253","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang, Y., Saleemi, I., & Shah, M. (2013). Discovering motion primitives for unsupervised grouping and one-shot learning of human actions, gestures, and expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(7), 1635\u20131648.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"939_CR88","unstructured":"Yilmaz, A., & Shah, M. (2005). Actions as objects: A novel action representation. In Proceedings of the IEEE conference on computer vision and pattern recognition."},{"key":"939_CR89","unstructured":"Yuan, J., Liu, Z., & Wu, Y. (2009). Discriminative subvolume search for efficient action detection. In Proceedings of the IEEE conference on computer vision and pattern recognition."},{"key":"939_CR90","unstructured":"Zhao, X., & Medioni, G. (2011). Robust unsupervised motion pattern inference from video and applications. In Proceedings of the international conference on computer vision."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0939-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-016-0939-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0939-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0939-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,12]],"date-time":"2019-09-12T06:27:41Z","timestamp":1568269661000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0939-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,10]]},"references-count":90,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["939"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0939-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,8,10]]}}}