{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:40:46Z","timestamp":1764783646575,"version":"3.40.3"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319105772"},{"type":"electronic","value":"9783319105789"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-10578-9_48","type":"book-chapter","created":{"date-parts":[[2014,8,13]],"date-time":"2014-08-13T20:51:57Z","timestamp":1407963117000},"page":"737-752","source":"Crossref","is-referenced-by-count":79,"title":["Spatio-temporal Object Detection Proposals"],"prefix":"10.1007","author":[{"given":"Dan","family":"Oneata","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jerome","family":"Revaud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakob","family":"Verbeek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"11","key":"48_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R. Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., S\u00fcsstrunk, S.: SLICsuperpixels compared to state-of-the-art superpixel methods. PAMI\u00a034(11), 2274\u20132282 (2012)","journal-title":"PAMI"},{"issue":"11","key":"48_CR2","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TPAMI.2012.28","volume":"34","author":"B. Alexe","year":"2012","unstructured":"Alexe, B., Deselares, T., Ferrari, V.: Measuring the objectness of image windows. PAMI\u00a034(11), 2189\u20132202 (2012)","journal-title":"PAMI"},{"issue":"5","key":"48_CR3","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P. Arbel\u00e1ez","year":"2011","unstructured":"Arbel\u00e1ez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. PAMI\u00a033(5), 898\u2013916 (2011)","journal-title":"PAMI"},{"key":"48_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-642-15555-0_21","volume-title":"Computer Vision \u2013 ECCV 2010","author":"T. Brox","year":"2010","unstructured":"Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol.\u00a06315, pp. 282\u2013295. Springer, Heidelberg (2010)"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Brox, T., Malik, J.: Large displacement optical flow: Descriptor matching in variational motion estimation. PAMI (2011)","DOI":"10.1109\/TPAMI.2010.143"},{"key":"48_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/978-3-642-33786-4_32","volume-title":"Computer Vision \u2013 ECCV 2012","author":"J. Carreira","year":"2012","unstructured":"Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Semantic segmentation with second-order pooling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol.\u00a07578, pp. 430\u2013443. Springer, Heidelberg (2012)"},{"key":"48_CR7","doi-asserted-by":"crossref","unstructured":"Chen, A., Corso, J.: Propagating multi-class pixel labels throughout video frames. In: Proceedings of Western New York Image Processing Workshop (2010)","DOI":"10.1109\/WNYIPW.2010.5649773"},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"Cinbis, R., Verbeek, J., Schmid, C.: Segmentation driven object detection with Fisher vectors. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.369"},{"issue":"5","key":"48_CR9","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/TMI.2007.912817","volume":"27","author":"J. Corso","year":"2008","unstructured":"Corso, J., Sharon, E., Dube, S., El-Saden, S., Sinha, U., Yuille, A.: Efficient multilevel brain tumor segmentation with integrated Bayesian model classification. IEEE Trans. Med. Imaging\u00a027(5), 629\u2013640 (2008)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"48_CR10","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Zitnick, C.: Structured forests for fast edge detection. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.231"},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459279"},{"key":"48_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/978-3-642-15555-0_42","volume-title":"Computer Vision \u2013 ECCV 2010","author":"I. Endres","year":"2010","unstructured":"Endres, I., Hoiem, D.: Category independent object proposals. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol.\u00a06315, pp. 575\u2013588. Springer, Heidelberg (2010)"},{"issue":"2","key":"48_CR13","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"P. Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV\u00a059(2), 167\u2013181 (2004)","journal-title":"IJCV"},{"issue":"2","key":"48_CR14","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1109\/TPAMI.2004.1262185","volume":"26","author":"C. Fowlkes","year":"2004","unstructured":"Fowlkes, C., Belongie, S., Chung, F., Malik, J.: Spectral grouping using the nystr\u00f6m method. PAMI\u00a026(2), 214\u2013225 (2004)","journal-title":"PAMI"},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Actom sequence models for efficient action detection. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995646"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Galasso, F., Nagaraja, N., Cardenas, T., Brox, T., Schiele, B.: A unified video segmentation benchmark: Annotation, metrics and analysis. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.438"},{"key":"48_CR17","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":"48_CR18","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"48_CR19","doi-asserted-by":"crossref","unstructured":"Jain, M., J\u00e9gou, H., Bouthemy, P.: Better exploiting motion for better action recognition. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.330"},{"key":"48_CR20","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J., Bouthemy, P., J\u00e9gou, H., Snoek, C.: Action localization with tubelets from motion. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.100"},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: A large video database for human motion recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"12","key":"48_CR22","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1109\/TPAMI.2009.144","volume":"31","author":"C. Lampert","year":"2009","unstructured":"Lampert, C., Blaschko, M., Hofmann, T.: Efficient subwindow search: a branch and bound framework for object localization. PAMI\u00a031(12), 2129\u20132142 (2009)","journal-title":"PAMI"},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Li, Z., Gavves, E., van de Sande, K., Snoek, C., Smeulders, A.: Codemaps, segment classify and search objects locally. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.454"},{"key":"48_CR24","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, H., Min, D., Do, M.: Patch match filter: Efficient edge-aware filtering meets randomized search for fast correspondence field estimation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.242"},{"key":"48_CR25","unstructured":"Ma, T., Latecki, L.: Maximum weight cliques with mutex constraints for video object segmentation. In: CVPR (2012)"},{"key":"48_CR26","doi-asserted-by":"crossref","unstructured":"Man\u00e9n, S., Guillaumin, M., Gool, L.V.: Prime object proposals with randomized Prim\u2019s algorithm. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.315"},{"key":"48_CR27","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"48_CR28","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Action and event recognition with Fisher vectors on a compact feature set. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.228"},{"key":"48_CR29","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Efficient action localization with approximately normalized Fisher vectors. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.326"},{"key":"48_CR30","unstructured":"Over, P., Awad, G., Michel, M., Fiscus, J., Sanders, G., Shaw, B., Kraaij, W., Smeaton, A., Qu\u00e9not, G.: TRECVID 2012 \u2013 an overview of the goals, tasks, data, evaluation mechanisms and metrics. In: Proceedings of TRECVID (2012)"},{"key":"48_CR31","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.223"},{"key":"48_CR32","doi-asserted-by":"crossref","unstructured":"Paris, S., Durand, F.: A topological approach to hierarchical segmentation using mean shift. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383228"},{"key":"48_CR33","doi-asserted-by":"crossref","unstructured":"Pele, O., Werman, M.: Fast and robust earth mover\u2019s distances. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459199"},{"key":"48_CR34","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"48_CR35","doi-asserted-by":"crossref","unstructured":"Rodriguez, M., Ahmed, J., Shah, M.: Action MACH: a spatio-temporal maximum average correlation height filter for action recognition. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"issue":"3","key":"48_CR36","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.: Image classification with the Fisher vector: Theory and practice. IJCV\u00a0105(3), 222\u2013245 (2013)","journal-title":"IJCV"},{"key":"48_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-642-15549-9_32","volume-title":"Computer Vision \u2013 ECCV 2010","author":"N. Sundaram","year":"2010","unstructured":"Sundaram, N., Brox, T., Keutzer, K.: Dense point trajectories by gpu-accelerated large displacement optical flow. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol.\u00a06311, pp. 438\u2013451. Springer, Heidelberg (2010)"},{"key":"48_CR38","doi-asserted-by":"crossref","unstructured":"Tran, D., Yuan, J.: Optimal spatio-temporal path discovery for video event detection. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995416"},{"issue":"2","key":"48_CR39","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"J. Uijlings","year":"2013","unstructured":"Uijlings, J., van de Sande, K., Gevers, T., Smeulders, A.: Selective search for object recognition. IJCV\u00a0104(2), 154\u2013171 (2013)","journal-title":"IJCV"},{"key":"48_CR40","doi-asserted-by":"crossref","unstructured":"van de Sande, K., Snoek, C., Smeulders, A.: Fisher and VLAD with FLAIR. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.304"},{"key":"48_CR41","doi-asserted-by":"crossref","unstructured":"Van den Bergh, M., Roig, G., Boix, X., Manen, S., Gool, L.V.: Online video SEEDS for temporal window objectness. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.54"},{"key":"48_CR42","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"48_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Yang, M., Zhu, S., Lin, Y.: Regionlets for generic object detection. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.10"},{"key":"48_CR44","doi-asserted-by":"crossref","unstructured":"Weber, O., Devir, Y., Bronstein, A., Bronstein, M., Kimmel, R.: Parallel algorithms for approximation of distance maps on parametric surfaces. ACM Trans. Graph. (2008)","DOI":"10.1145\/1409625.1409626"},{"key":"48_CR45","unstructured":"Xu, C., Corso, J.: Evaluation of super-voxel methods for early video processing. In: CVPR (2012)"},{"key":"48_CR46","doi-asserted-by":"crossref","unstructured":"Xu, C., Whitt, S., Corso, J.: Flattening supervoxel hierarchies by the uniform entropy slice. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.279"},{"key":"48_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/978-3-642-33783-3_45","volume-title":"Computer Vision \u2013 ECCV 2012","author":"C. Xu","year":"2012","unstructured":"Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol.\u00a07577, pp. 626\u2013639. Springer, Heidelberg (2012)"},{"key":"48_CR48","unstructured":"Yuan, J., Liu, Z., Wu, Y.: Discriminative subvolume search for efficient action detection. In: CVPR (2009)"},{"key":"48_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.87"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2014"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10578-9_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T10:07:25Z","timestamp":1575281245000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10578-9_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105772","9783319105789"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10578-9_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}