{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T06:10:02Z","timestamp":1746339002978,"version":"3.40.4"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319105925"},{"type":"electronic","value":"9783319105932"}],"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\/978-3-319-10593-2_42","type":"book-chapter","created":{"date-parts":[[2014,8,14]],"date-time":"2014-08-14T06:52:23Z","timestamp":1407999143000},"page":"640-655","source":"Crossref","is-referenced-by-count":34,"title":["Video Object Discovery and Co-segmentation with Extremely Weak Supervision"],"prefix":"10.1007","author":[{"given":"Le","family":"Wang","sequence":"first","affiliation":[]},{"given":"Gang","family":"Hua","sequence":"additional","affiliation":[]},{"given":"Rahul","family":"Sukthankar","sequence":"additional","affiliation":[]},{"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"11","key":"42_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., Susstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. TPAMI\u00a034(11), 2274\u20132282 (2012)","journal-title":"TPAMI"},{"key":"42_CR2","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":"42_CR3","doi-asserted-by":"crossref","unstructured":"Avidan, S.: SpatialBoost: Adding spatial reasoning to adaboost. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. Part IV. LNCS, vol.\u00a03954, pp. 386\u2013396. Springer, Heidelberg (2006)","DOI":"10.1007\/11744085_30"},{"key":"42_CR4","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1145\/1531326.1531376","volume":"28","author":"X. Bai","year":"2009","unstructured":"Bai, X., Wang, J., Simons, D., Sapiro, G.: Video SnapCut: robust video object cutout using localized classifiers. ACM Trans. on Graphics\u00a028, 70 (2009)","journal-title":"ACM Trans. on Graphics"},{"key":"42_CR5","doi-asserted-by":"crossref","unstructured":"Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: iCoseg: Interactive co-segmentation with intelligent scribble guidance. In: CVPR, pp. 3169\u20133176 (2010)","DOI":"10.1109\/CVPR.2010.5540080"},{"issue":"2","key":"42_CR6","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11263-006-7934-5","volume":"70","author":"Y. Boykov","year":"2006","unstructured":"Boykov, Y., Funka-Lea, G.: Graph cuts and efficient ND image segmentation. IJCV\u00a070(2), 109\u2013131 (2006)","journal-title":"IJCV"},{"issue":"9","key":"42_CR7","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1109\/TPAMI.2004.60","volume":"26","author":"Y. Boykov","year":"2004","unstructured":"Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut\/max-flow algorithms for energy minimization in vision. TPAMI\u00a026(9), 1124\u20131137 (2004)","journal-title":"TPAMI"},{"key":"42_CR8","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":"42_CR9","doi-asserted-by":"crossref","unstructured":"Chen, D.J., Chen, H.T., Chang, L.W.: Video object cosegmentation. In: ACM Multimedia, pp. 805\u2013808 (2012)","DOI":"10.1145\/2393347.2396317"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Chiu, W.C., Fritz, M.: Multi-class video co-segmentation with a generative multi-video model. In: CVPR, pp. 321\u2013328 (2013)","DOI":"10.1109\/CVPR.2013.48"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Dai, J., Wu, Y.N., Zhou, J., Zhu, S.C.: Cosegmentation and cosketch by unsupervised learning. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.165"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: CVPR, pp. 2141\u20132148 (2010)","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Guo, J., Li, Z., Cheong, L.F., Zhou, S.Z.: Video co-segmentation for meaningful action extraction. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.278"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., Perona, P., et al.: Graph-based visual saliency. In: NIPS, pp. 545\u2013552 (2006)","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Joulin, A., Bach, F., Ponce, J.: Discriminative clustering for image co-segmentation. In: CVPR, pp. 1943\u20131950 (2010)","DOI":"10.1109\/CVPR.2010.5539868"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: ICCV, pp. 1995\u20132002 (2011)","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.273"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Liu, D., Chen, T.: A topic-motion model for unsupervised video object discovery. In: CVPR, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383220"},{"issue":"12","key":"42_CR19","doi-asserted-by":"publisher","first-page":"2178","DOI":"10.1109\/TPAMI.2010.31","volume":"32","author":"D. Liu","year":"2010","unstructured":"Liu, D., Hua, G., Chen, T.: A hierarchical visual model for video object summarization. TPAMI\u00a032(12), 2178\u20132190 (2010)","journal-title":"TPAMI"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Ma, T., Latecki, L.J.: Maximum weight cliques with mutex constraints for video object segmentation. In: CVPR, pp. 670\u2013677 (2012)","DOI":"10.1109\/CVPR.2012.6247735"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Ochs, P., Brox, T.: Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions. In: ICCV, pp. 1583\u20131590 (2011)","DOI":"10.1109\/ICCV.2011.6126418"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Ochs, P., Brox, T.: Higher order motion models and spectral clustering. In: CVPR, pp. 614\u2013621 (2012)","DOI":"10.1109\/CVPR.2012.6247728"},{"key":"42_CR23","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":"42_CR24","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"},{"key":"42_CR25","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":"42_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-3-642-33712-3_7","volume-title":"Computer Vision \u2013 ECCV 2012","author":"M. Rubinstein","year":"2012","unstructured":"Rubinstein, M., Liu, C., Freeman, W.T.: Annotation propagation in large image databases via dense image correspondence. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol.\u00a07574, pp. 85\u201399. Springer, Heidelberg (2012)"},{"key":"42_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-642-37444-9_2","volume-title":"Computer Vision \u2013 ACCV 2012","author":"J.C. Rubio","year":"2013","unstructured":"Rubio, J.C., Serrat, J., L\u00f3pez, A.: Video co-segmentation. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part II. LNCS, vol.\u00a07725, pp. 13\u201324. Springer, Heidelberg (2013)"},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Tang, K., Sukthankar, R., Yagnik, J., Fei-Fei, L.: Discriminative segment annotation in weakly labeled video. In: CVPR, pp. 2483\u20132490 (2013)","DOI":"10.1109\/CVPR.2013.321"},{"key":"42_CR29","doi-asserted-by":"crossref","unstructured":"Tiburzi, F., Escudero, M., Besc\u00f3s, J., Mart\u00ednez, J.M.: A ground truth for motion-based video-object segmentation. In: ICIP, pp. 17\u201320 (2008)","DOI":"10.1109\/ICIP.2008.4711680"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Tsai, D., Flagg, M., Rehg, J.: Motion coherent tracking with multi-label MRF optimization. In: BMVC (2010)","DOI":"10.5244\/C.24.56"},{"key":"42_CR31","doi-asserted-by":"crossref","unstructured":"Tu, Z.: Auto-context and its application to high-level vision tasks. In: CVPR, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587436"},{"issue":"2","key":"42_CR32","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(2), 284\u2013302 (2010)","journal-title":"IJCV"},{"key":"42_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/978-3-642-15552-9_34","volume-title":"Computer Vision \u2013 ECCV 2010","author":"S. Vicente","year":"2010","unstructured":"Vicente, S., Kolmogorov, V., Rother, C.: Cosegmentation revisited: Models and optimization. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 465\u2013479. Springer, Heidelberg (2010)"},{"key":"42_CR34","doi-asserted-by":"crossref","unstructured":"Vicente, S., Rother, C., Kolmogorov, V.: Object cosegmentation. In: CVPR, pp. 2217\u20132224 (2011)","DOI":"10.1109\/CVPR.2011.5995530"},{"key":"42_CR35","unstructured":"Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: NIPS, pp. 1417\u20131424 (2005)"},{"key":"42_CR36","doi-asserted-by":"crossref","unstructured":"Wang, L., Xue, J., Zheng, N., Hua, G.: Automatic salient object extraction with contextual cue. In: ICCV, pp. 105\u2013112 (2011)","DOI":"10.1109\/ICCV.2011.6126231"},{"key":"42_CR37","unstructured":"Wang, L., Xue, J., Zheng, N., Hua, G.: Concurrent segmentation of categorized objects from an image collection. In: ICPR, pp. 3309\u20133312 (2012)"},{"key":"42_CR38","doi-asserted-by":"crossref","unstructured":"Wang, L., Hua, G., Xue, J., Gao, Z., Zheng, N.: Joint segmentation and recognition of categorized objects from noisy web image collection. TIP (2014)","DOI":"10.1109\/TIP.2014.2339196"},{"issue":"9","key":"42_CR39","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TPAMI.2011.236","volume":"34","author":"L. Xu","year":"2012","unstructured":"Xu, L., Jia, J., Matsushita, Y.: Motion detail preserving optical flow estimation. TPAMI\u00a034(9), 1744\u20131757 (2012)","journal-title":"TPAMI"},{"issue":"11","key":"42_CR40","first-page":"2874","volume":"46","author":"J. Xue","year":"2013","unstructured":"Xue, J., Wang, L., Zheng, N., Hua, G.: Automatic salient object extraction with contextual cue and its applications to recognition and alpha matting. PR\u00a046(11), 2874\u20132889 (2013)","journal-title":"PR"},{"key":"42_CR41","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, pp. 628\u2013635 (2013)","DOI":"10.1109\/CVPR.2013.87"},{"key":"42_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, G., Yuan, J., Hua, G.: Topical video object discovery from key frames by modeling word co-occurrence prior. In: CVPR, pp. 1602\u20131609 (2013)","DOI":"10.1109\/CVPR.2013.210"}],"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\/978-3-319-10593-2_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T05:36:59Z","timestamp":1746337019000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10593-2_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105925","9783319105932"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10593-2_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}