The Experts below are selected from a list of 69681 Experts worldwide ranked by ideXlab platform
Martin Byrod - One of the best experts on this subject based on the ideXlab platform.
-
optimizing visual vocabularies using soft assignment entropies
6495 pp 255-268 (2011), 2011Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance. (Less)
-
optimizing visual vocabularies using soft assignment entropies
Asian Conference on Computer Vision, 2010Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance.
Yubin Kuang - One of the best experts on this subject based on the ideXlab platform.
-
optimizing visual vocabularies using soft assignment entropies
6495 pp 255-268 (2011), 2011Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance. (Less)
-
optimizing visual vocabularies using soft assignment entropies
Asian Conference on Computer Vision, 2010Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance.
Magnus Oskarsson - One of the best experts on this subject based on the ideXlab platform.
-
optimizing visual vocabularies using soft assignment entropies
6495 pp 255-268 (2011), 2011Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance. (Less)
-
optimizing visual vocabularies using soft assignment entropies
Asian Conference on Computer Vision, 2010Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance.
Lars Kopp - One of the best experts on this subject based on the ideXlab platform.
-
optimizing visual vocabularies using soft assignment entropies
6495 pp 255-268 (2011), 2011Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance. (Less)
-
optimizing visual vocabularies using soft assignment entropies
Asian Conference on Computer Vision, 2010Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance.
Karl Johan Astrom - One of the best experts on this subject based on the ideXlab platform.
-
optimizing visual vocabularies using soft assignment entropies
6495 pp 255-268 (2011), 2011Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance. (Less)
-
optimizing visual vocabularies using soft assignment entropies
Asian Conference on Computer Vision, 2010Co-Authors: Yubin Kuang, Karl Johan Astrom, Lars Kopp, Magnus Oskarsson, Martin ByrodAbstract:The state of the art for large Database Object retrieval in images is based on quantizing descriptors of interest points into visual words. High similarity between matching image representations (as bags of words) is based upon the assumption that matched points in the two images end up in similar words in hard assignment or in similar representations in soft assignment techniques. In this paper we study how ground truth correspondences can be used to generate better visual vocabularies. Matching of image patches can be done e.g. using deformable models or from estimating 3D geometry. For optimization of the vocabulary, we propose minimizing the entropies of soft assignment of points. We base our clustering on hierarchical k-splits. The results from our entropy based clustering are compared with hierarchical k-means. The vocabularies have been tested on real data with decreased entropy and increased true positive rate, as well as better retrieval performance.
