Linear spatial pyramid matching using sparse coding for image classification
Citations
30,811 citations
14,807 citations
12,783 citations
Additional excerpts
...[17] 73....
[...]
6,061 citations
5,919 citations
Cites methods from "Linear spatial pyramid matching usi..."
..., [17], [18], [19]) and detection (e....
[...]
..., by vector quantization [15], [16], [30], sparse coding [17], [18], or Fisher kernels [19]....
[...]
...Second, the full-image view is methodologically consistent with the traditional methods [15], [17], [19] where the encoded SIFT vectors of the entire image are pooled together....
[...]
References
40,826 citations
"Linear spatial pyramid matching usi..." refers methods in this paper
...The KSPM was trained using the LIBSVM [4] package....
[...]
8,736 citations
"Linear spatial pyramid matching usi..." refers background or methods in this paper
...However, their performances are still behind the state-of-the-art achieved by [12, 1, 9] on public benchmarks....
[...]
...In the experiments, we implemented and evaluated three classes of SPM methods on four diverse datasets: Caltech 101 [14], Caltech 256 [8], 15 Scenes [12], and TRECVID 2008 surveillance video....
[...]
...By overcoming this problem, one particular extension of the BoF model, called spatial pyramid matching (SPM) [12], has made a remarkable success on a range of image classification benchmarks like Caltech101 [14] and Caltech-256 [8], and was the major compoFigure 1....
[...]
...[12], we took 100 images per class for training and used the left for testing....
[...]
...50 KSPM [12] 56....
[...]
6,882 citations
"Linear spatial pyramid matching usi..." refers methods in this paper
...We also tried our algorithm on the 15-Scenes dataset compiled by several researchers [ 20 , 7, 12]....
[...]
5,493 citations
"Linear spatial pyramid matching usi..." refers background or methods in this paper
...Over the years many works have been done to improve the traditional BoF model, such as generative methods in [7, 21, 3, 1] for modeling the co-occurrence of the codewords or descriptors, discriminative codebook learning in [10, 5, 19, 27] instead of standard unsupervised K-means clustering, and spatial pyramid matching kernel (SPM) [12] for modeling the spatial layout of the local features, all bringing promising progress....
[...]
...Sparse modeling of image patches has been successfully applied to tasks such as image and video denoising, inpainting, demosaicing, super-resolution[5, 17, 26] and segmentation [18]....
[...]
3,920 citations
"Linear spatial pyramid matching usi..." refers background or methods in this paper
...We also tried our algorithm on the 15-Scenes dataset compiled by several researchers [20, 7, 12]....
[...]
...Over the years many works have been done to improve the traditional BoF model, such as generative methods in [7, 21, 3, 1] for modeling the co-occurrence of the codewords or descriptors, discriminative codebook learning in [10, 5, 19, 27] instead of standard unsupervised K-means clustering, and spatial pyramid matching kernel (SPM) [12] for modeling the spatial layout of the local features, all bringing promising progress....
[...]