{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:37:03Z","timestamp":1743136623447,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319105987"},{"type":"electronic","value":"9783319105994"}],"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\/978-3-319-10599-4_27","type":"book-chapter","created":{"date-parts":[[2014,8,14]],"date-time":"2014-08-14T03:37:13Z","timestamp":1407987433000},"page":"415-430","source":"Crossref","is-referenced-by-count":3,"title":["Discovering Object Classes from Activities"],"prefix":"10.1007","author":[{"given":"Abhilash","family":"Srikantha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juergen","family":"Gall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: CVPR, pp. 73\u201380 (2010)","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"27_CR2","unstructured":"Blaschko, M.B., Vedaldi, A., Zisserman, A.: Simultaneous object detection and ranking with weak supervision. In: NIPS, pp. 235\u2013243 (2010)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: ACM Int. Conf. on Image and Video Retrieval, pp. 401\u2013408 (2007)","DOI":"10.1145\/1282280.1282340"},{"key":"27_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)"},{"issue":"3","key":"27_CR5","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","volume":"33","author":"T. Brox","year":"2011","unstructured":"Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. PAMI\u00a033(3), 500\u2013513 (2011)","journal-title":"PAMI"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chum, O., Zisserman, A.: An exemplar model for learning object classes. In: CVPR, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383050"},{"issue":"5","key":"27_CR7","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D. Comaniciu","year":"2002","unstructured":"Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. PAMI\u00a024(5), 603\u2013619 (2002)","journal-title":"PAMI"},{"key":"27_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/978-3-642-33783-3_21","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V. Delaitre","year":"2012","unstructured":"Delaitre, V., Fouhey, D.F., Laptev, I., Sivic, J., Gupta, A., Efros, A.A.: Scene semantics from long-term observation of people. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol.\u00a07577, pp. 284\u2013298. Springer, Heidelberg (2012)"},{"key":"27_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/978-3-642-15561-1_33","volume-title":"Computer Vision \u2013 ECCV 2010","author":"T. Deselaers","year":"2010","unstructured":"Deselaers, T., Alexe, B., Ferrari, V.: Localizing objects while learning their appearance. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.\u00a06314, pp. 452\u2013466. Springer, Heidelberg (2010)"},{"key":"27_CR10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M. Everingham","year":"2010","unstructured":"Everingham, M., Gool, L.V., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV\u00a088, 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.: Learning to recognize objects in egocentric activities. In: CVPR, pp. 3281\u20133288 (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"issue":"2","key":"27_CR12","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"P.F. Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV\u00a059(2), 167\u2013181 (2004)","journal-title":"IJCV"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Filipovych, R., Ribeiro, E.: Recognizing primitive interactions by exploring actor-object states. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587726"},{"key":"27_CR14","unstructured":"Human Body Analysis. In: Fossati, A., Gall, J., Grabner, H., Ren, X., Konolige, K. (eds.) Consumer Depth Cameras for Computer Vision. Springer (2013)"},{"key":"27_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-642-33715-4_53","volume-title":"Computer Vision \u2013 ECCV 2012","author":"D.F. Fouhey","year":"2012","unstructured":"Fouhey, D.F., Delaitre, V., Gupta, A., Efros, A.A., Laptev, I., Sivic, J.: People watching: Human actions as a cue for single view geometry. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol.\u00a07576, pp. 732\u2013745. Springer, Heidelberg (2012)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Gall, J., Fossati, A., van Gool, L.: Functional categorization of objects using real-time markerless motion capture. In: CVPR, pp. 1969\u20131976 (2011)","DOI":"10.1109\/CVPR.2011.5995582"},{"issue":"11","key":"27_CR17","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.1109\/TPAMI.2011.70","volume":"33","author":"J. Gall","year":"2011","unstructured":"Gall, J., Yao, A., Razavi, N., Van Gool, L., Lempitsky, V.: Hough forests for object detection, tracking, and action recognition. PAMI\u00a033(11), 2188\u20132202 (2011)","journal-title":"PAMI"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: CVPR, pp. 1529\u20131536 (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, A., Davis, L.: Objects in action: An approach for combining action understanding and object perception. In: CVPR, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383331"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Gupta, A., Satkin, S., Efros, A.A., Hebert, M.: From 3D scene geometry to human workspace. In: CVPR, pp. 1961\u20131968 (2011)","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Koppula, H., Saxena, A.: Hallucinated humans as the hidden context for labeling 3D scenes. In: CVPR, pp. 2993\u20133000 (2013)","DOI":"10.1109\/CVPR.2013.385"},{"issue":"1","key":"27_CR22","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1023\/A:1013200319198","volume":"46","author":"M. Jones","year":"2002","unstructured":"Jones, M., Rehg, J.: Statistical color models with application to skin detection. IJCV\u00a046(1), 81\u201396 (2002)","journal-title":"IJCV"},{"key":"27_CR23","first-page":"81","volume":"115","author":"H. Kjellstr\u00f6m","year":"2010","unstructured":"Kjellstr\u00f6m, H., Romero, J., Kragic, D.: Visual object-action recognition: Inferring object affordances from human demonstration. CVIU\u00a0115, 81\u201390 (2010)","journal-title":"CVIU"},{"issue":"10","key":"27_CR24","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1109\/TPAMI.2006.200","volume":"28","author":"V. Kolmogorov","year":"2006","unstructured":"Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. PAMI\u00a028(10), 1568\u20131583 (2006)","journal-title":"PAMI"},{"issue":"8","key":"27_CR25","first-page":"951","volume":"32","author":"H. Koppula","year":"2013","unstructured":"Koppula, H., Gupta, R., Saxena, A.: Learning human activities and object affordances from rgb-d videos. IJRR\u00a032(8), 951\u2013970 (2013)","journal-title":"IJRR"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Grauman, K.: Learning the easy things first: Self-paced visual category discovery. In: CVPR, pp. 1721\u20131728 (2011)","DOI":"10.1109\/CVPR.2011.5995523"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Leistner, C., Godec, M., Schulter, S., Saffari, A., Werlberger, M., Bischof, H.: Improving classifiers with unlabeled weakly-related videos. In: CVPR, pp. 2753\u20132760 (2011)","DOI":"10.1109\/CVPR.2011.5995475"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Manen, S., Guillaumin, M., Van Gool, L.: Prime object proposals with randomized prim\u2019s algorithm. In: ICCV, pp. 2536\u20132543 (2013)","DOI":"10.1109\/ICCV.2013.315"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Moore, D., Essa, I., Hayes, M.: Exploiting human actions and object context for recognition tasks. In: ICCV, pp. 80\u201386 (1999)","DOI":"10.1109\/ICCV.1999.791201"},{"key":"27_CR30","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s11263-009-0211-7","volume":"83","author":"B. Ommer","year":"2009","unstructured":"Ommer, B., Mader, T., Buhmann, J.: Seeing the Objects Behind the Dots: Recognition in Videos from a Moving Camera. IJCV\u00a083, 57\u201371 (2009)","journal-title":"IJCV"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Peursum, P., West, G., Venkatesh, S.: Combining image regions and human activity for indirect object recognition in indoor wide-angle views. In: ICCV, pp. 82\u201389 (2005)","DOI":"10.1109\/ICCV.2005.57"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Pieropan, A., Ek, C.H., Kjellstrom, H.: Functional object descriptors for human activity modeling. In: ICRA, pp. 1282\u20131289 (2013)","DOI":"10.1109\/ICRA.2013.6630736"},{"key":"27_CR33","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, pp. 3282\u20133289 (2012)","DOI":"10.1109\/CVPR.2012.6248065"},{"issue":"8","key":"27_CR34","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1109\/TPAMI.2006.155","volume":"28","author":"D. Ramanan","year":"2006","unstructured":"Ramanan, D., Forsyth, D.A., Barnard, K.: Building models of animals from video. PAMI\u00a028(8), 1319\u20131334 (2006)","journal-title":"PAMI"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: CVPR, pp. 1194\u20131201 (2012)","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Rubinstein, M., Joulin, A., Kopf, J., Liu, C.: Unsupervised joint object discovery and segmentation in internet images. In: CVPR, pp. 1939\u20131946 (2013)","DOI":"10.1109\/CVPR.2013.253"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Schulter, S., Leistner, C., Roth, P.M., Bischof, H.: Unsupervised object discovery and segmentation in videos. In: BMVC, pp. 391\u2013404 (2013)","DOI":"10.5244\/C.27.53"},{"key":"27_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-642-15552-9_48","volume-title":"Computer Vision \u2013 ECCV 2010","author":"M.W. Turek","year":"2010","unstructured":"Turek, M.W., Hoogs, A., Collins, R.: Unsupervised learning of functional categories in video scenes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 664\u2013677. Springer, Heidelberg (2010)"},{"key":"27_CR39","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/s11263-009-0271-8","volume":"88","author":"T. Tuytelaars","year":"2010","unstructured":"Tuytelaars, T., Lampert, C.H., Blaschko, M.B., Buntine, W.: Unsupervised object discovery: A comparison. IJCV\u00a088, 284\u2013302 (2010)","journal-title":"IJCV"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Winn, J.M., Jojic, N.: Locus: Learning object classes with unsupervised segmentation. In: ICCV, pp. 756\u2013763 (2005)","DOI":"10.1109\/ICCV.2005.148"}],"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\/978-3-319-10599-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T09:31:41Z","timestamp":1575279101000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10599-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105987","9783319105994"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10599-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}