"\u010Cech, Jan" . . "Omnipress" . "Per\u010Foch, Michal" . "2008-06-24+02:00"^^ . "978-1-4244-2242-5" . . "Matas, Ji\u0159\u00ED" . "21230" . "Efficient Sequential Correspondence Selection by Cosegmentation"@en . . "Efficient Sequential Correspondence Selection by Cosegmentation"@cs . . . "Anchorage, Alaska" . "RIV/68407700:21230/08:03150796!RIV09-MSM-21230___" . . . "RIV/68407700:21230/08:03150796" . "In many retrieval, object recognition and wide baseline stereo methods, correspondences of interest points (distinguished regions, transformation covariant points) are established possibly sublinearly by matching a compact descriptor such as SIFT. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that has (i) high precision (is highly discriminative) (ii) good recall and (iii) is fast. The sequential decision on the correctness of a correspondence is based on trivial attributes of a modified dense stereo matching algorithm. The attributes are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed for SVM projection computed on progressively larger co-segmented regions. Experimentally we show that the process significantly outperforms the standard correspondence selection process based on SIFT distance ratios on challenging mat"@en . . "Medison" . "Efficient Sequential Correspondence Selection by Cosegmentation" . "Efficient Sequential Correspondence Selection by Cosegmentation"@cs . . "In many retrieval, object recognition and wide baseline stereo methods, correspondences of interest points (distinguished regions, transformation covariant points) are established possibly sublinearly by matching a compact descriptor such as SIFT. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that has (i) high precision (is highly discriminative) (ii) good recall and (iii) is fast. The sequential decision on the correctness of a correspondence is based on trivial attributes of a modified dense stereo matching algorithm. The attributes are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed for SVM projection computed on progressively larger co-segmented regions. Experimentally we show that the process significantly outperforms the standard correspondence selection process based on SIFT distance ratios on challenging mat"@cs . . "3"^^ . "In many retrieval, object recognition and wide baseline stereo methods, correspondences of interest points (distinguished regions, transformation covariant points) are established possibly sublinearly by matching a compact descriptor such as SIFT. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that has (i) high precision (is highly discriminative) (ii) good recall and (iii) is fast. The sequential decision on the correctness of a correspondence is based on trivial attributes of a modified dense stereo matching algorithm. The attributes are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed for SVM projection computed on progressively larger co-segmented regions. Experimentally we show that the process significantly outperforms the standard correspondence selection process based on SIFT distance ratios on challenging mat" . "Efficient Sequential Correspondence Selection by Cosegmentation"@en . "P(1ET101210406), P(7E08031), S" . . . "1063-6919" . . "365505" . "8"^^ . "RANSAC; SIFT; SVM; correspondence; dense stereo; growing; image retrieval; learning; sequential decison; verification; wide-baseline stereo"@en . "3"^^ . . . . . . . . . "000259736800134" . "Efficient Sequential Correspondence Selection by Cosegmentation" . "CVPR 2008: Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition" . . "[7F2554B951C9]" . . . . . . .