PASCAL VOC Challenge performance evaluation and download server |
|
| Home | Leaderboard |
Classification Results: VOC2010 BETA
Competition "comp1" (train on VOC2010 data)
This leaderboard shows only those submissions that have been marked as public, and so the displayed rankings should not be considered as definitive.- The highest scoring entry in each column is shown in bold.
- Clicking on the blue arrow symbol (
) at the top of a column will order
the submissions from high to low wrt performance on that column.
Average Precision (AP %)
| mean | aero plane  | bicycle | bird | boat | bottle | bus | car | cat | chair | cow | dining table | dog | horse | motor bike | person | potted plant | sheep | sofa | train | tv/ monitor | submission date | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| KernelRegFusing [?] | 73.8 | 93.0 | 79.0 | 71.6 | 77.8 | 54.3 | 85.2 | 78.6 | 78.8 | 64.5 | 64.0 | 62.7 | 69.6 | 82.0 | 84.5 | 91.6 | 48.6 | 64.9 | 59.7 | 89.4 | 76.4 | 30-Aug-2010 | |
| KernelRegFusing [?] | 73.7 | 92.8 | 79.2 | 70.9 | 78.1 | 54.2 | 85.2 | 78.9 | 78.5 | 64.4 | 64.5 | 63.2 | 68.7 | 81.6 | 84.5 | 91.3 | 48.4 | 65.0 | 59.5 | 89.3 | 76.0 | 30-Aug-2010 | |
| MFDETSVM [?] | 72.1 | 91.9 | 77.1 | 69.5 | 74.7 | 52.5 | 84.3 | 77.3 | 76.2 | 63.0 | 63.5 | 62.9 | 65.0 | 79.5 | 83.2 | 91.2 | 45.5 | 65.4 | 55.0 | 87.0 | 77.2 | 30-Aug-2010 | |
| Exclusive-Classifier [?] | 71.5 | 91.3 | 77.1 | 70.0 | 75.6 | 50.7 | 83.2 | 77.1 | 75.4 | 62.5 | 62.6 | 62.7 | 64.6 | 77.9 | 81.8 | 91.1 | 44.8 | 64.3 | 53.2 | 86.3 | 77.1 | 30-Aug-2010 | |
| NLPR_VSTAR_CLS_DICTLEARN [?] | 71.2 | 90.3 | 77.0 | 65.3 | 75.0 | 53.7 | 85.9 | 80.5 | 74.6 | 62.9 | 66.2 | 54.1 | 66.8 | 76.1 | 81.7 | 89.9 | 41.6 | 66.3 | 57.0 | 85.0 | 74.3 | 30-Aug-2010 | |
| hog, lbp, nonlinear coding, svm, detection [?] | 70.9 | 93.3 | 73.0 | 69.9 | 77.2 | 47.9 | 85.7 | 79.7 | 79.4 | 61.7 | 56.6 | 61.1 | 71.1 | 76.7 | 79.3 | 86.8 | 38.1 | 63.9 | 55.8 | 87.5 | 72.9 | 30-Aug-2010 | |
| hog, lbp, nonlinear coding, svm [?] | 69.6 | 93.3 | 71.7 | 69.9 | 76.9 | 42.0 | 85.3 | 77.4 | 79.4 | 60.0 | 55.9 | 60.6 | 71.1 | 75.7 | 77.7 | 86.8 | 33.5 | 61.5 | 55.8 | 87.5 | 69.9 | 30-Aug-2010 | |
| BW+New Colour SIFT [?] | 69.3 | 91.5 | 71.0 | 67.3 | 70.0 | 43.9 | 80.6 | 75.3 | 73.4 | 59.3 | 57.8 | 60.8 | 64.0 | 70.6 | 80.0 | 88.6 | 50.9 | 65.6 | 56.1 | 83.0 | 76.2 | 30-Aug-2010 | |
| BW+New Colour SIFT-SRKDA [?] | 69.0 | 90.6 | 66.9 | 63.4 | 70.2 | 49.4 | 81.9 | 76.7 | 71.0 | 60.0 | 57.1 | 60.5 | 64.5 | 67.4 | 79.1 | 90.2 | 53.3 | 63.5 | 58.0 | 81.9 | 74.4 | 30-Aug-2010 | |
| CVC_Plus_Det [?] | 67.8 | 91.7 | 70.0 | 66.8 | 71.3 | 49.1 | 81.4 | 77.5 | 71.2 | 60.0 | 52.6 | 55.7 | 61.0 | 70.9 | 76.7 | 88.4 | 43.2 | 59.7 | 53.8 | 84.7 | 71.3 | 30-Aug-2010 | |
| Multikernel+KDA [?] | 66.5 | 90.6 | 66.1 | 67.2 | 70.6 | 36.0 | 79.7 | 69.8 | 73.4 | 58.4 | 50.7 | 60.1 | 65.2 | 69.8 | 76.9 | 87.0 | 42.5 | 59.6 | 49.9 | 85.2 | 71.3 | 30-Aug-2010 | |
| CVC_Plus [?] | 64.4 | 91.0 | 61.8 | 66.7 | 71.1 | 37.7 | 78.9 | 67.8 | 72.2 | 55.8 | 51.0 | 55.8 | 59.4 | 65.3 | 73.0 | 84.0 | 39.9 | 56.9 | 48.5 | 83.9 | 68.1 | 30-Aug-2010 | |
| FU-SVM-SIFT [?] | 63.9 | 89.7 | 63.9 | 64.5 | 68.3 | 36.8 | 77.9 | 68.5 | 72.0 | 57.2 | 47.2 | 56.7 | 63.5 | 66.8 | 74.2 | 85.0 | 32.8 | 54.3 | 49.1 | 82.6 | 66.8 | 30-Aug-2010 | |
| Bonn_FGT_Segm [?] | 61.4 | 88.0 | 61.6 | 53.1 | 63.3 | 34.8 | 77.5 | 72.3 | 71.1 | 41.1 | 56.0 | 39.7 | 64.4 | 68.9 | 75.4 | 87.5 | 32.5 | 59.3 | 40.8 | 78.8 | 61.4 | 30-Aug-2010 | |
| Improved Fisher Vector [?] | 61.2 | 87.1 | 59.6 | 59.9 | 69.7 | 31.3 | 76.4 | 62.9 | 64.3 | 52.5 | 42.4 | 55.1 | 59.7 | 64.3 | 70.4 | 83.9 | 32.6 | 53.3 | 50.4 | 80.0 | 67.6 | 10-Aug-2010 | |
| CVC_Flat [?] | 61.1 | 89.4 | 57.6 | 63.0 | 68.5 | 32.0 | 76.7 | 64.7 | 66.9 | 51.5 | 48.4 | 50.0 | 54.8 | 63.1 | 69.9 | 83.5 | 33.7 | 54.8 | 46.1 | 82.2 | 65.9 | 30-Aug-2010 | |
| LIRIS_Multi-Feature_MKL_trainval [?] | 60.0 | 87.5 | 57.0 | 61.7 | 68.3 | 29.9 | 76.6 | 61.9 | 67.5 | 56.9 | 35.1 | 50.6 | 55.1 | 62.2 | 69.3 | 83.6 | 35.9 | 52.9 | 42.8 | 79.8 | 66.3 | 28-Aug-2010 | |
| SIFT-GMM-MKL [?] | 58.9 | 87.2 | 56.6 | 59.6 | 66.0 | 32.6 | 72.7 | 63.1 | 64.8 | 54.6 | 41.2 | 49.3 | 58.8 | 59.1 | 68.2 | 82.9 | 31.2 | 49.2 | 43.2 | 75.0 | 63.4 | 30-Aug-2010 | |
| Ritsu_CBVR_WKF [?] | 57.4 | 85.6 | 57.2 | 54.9 | 64.5 | 29.2 | 71.2 | 57.1 | 63.2 | 53.9 | 37.6 | 49.6 | 54.7 | 58.7 | 67.9 | 80.1 | 29.2 | 52.2 | 43.5 | 76.4 | 60.9 | 30-Aug-2010 | |
| SVM_WHGO_SIFT_CENTRIST_low-level modeling [?] | 57.1 | 83.5 | 54.2 | 55.2 | 66.8 | 28.5 | 72.1 | 65.4 | 64.2 | 51.9 | 36.1 | 49.3 | 55.6 | 58.0 | 66.5 | 82.1 | 25.3 | 48.1 | 41.7 | 78.4 | 59.5 | 23-Aug-2010 | |
| UC3M_Generative_Discriminative [?] | 57.1 | 85.5 | 51.6 | 55.4 | 64.8 | 25.9 | 74.4 | 60.6 | 66.0 | 51.0 | 45.9 | 43.9 | 55.0 | 59.0 | 65.2 | 80.3 | 24.1 | 51.4 | 47.0 | 76.4 | 58.6 | 30-Aug-2010 | |
| SVM_LDP_SIFT_PMK_SPMK [?] | 56.4 | 86.1 | 59.3 | 60.2 | 68.7 | 28.7 | 74.8 | 63.5 | 68.0 | 52.5 | 41.4 | 47.1 | 57.5 | 60.9 | 68.2 | 81.5 | 29.4 | 52.1 | 44.5 | 79.1 | 4.7 | 25-Aug-2010 | |
| LIP6_MKL_L1 [?] | 55.5 | 78.5 | 55.9 | 54.6 | 62.5 | 25.0 | 69.3 | 59.5 | 60.0 | 51.3 | 37.9 | 46.7 | 54.0 | 60.5 | 64.0 | 72.8 | 32.8 | 52.6 | 38.5 | 72.7 | 61.1 | 24-Aug-2010 | |
| LIP6_KSVM_Baseline [?] | 54.2 | 78.5 | 54.1 | 49.9 | 61.1 | 24.7 | 68.3 | 58.0 | 59.9 | 50.7 | 35.7 | 42.6 | 55.0 | 60.9 | 63.1 | 71.1 | 25.9 | 51.5 | 39.9 | 74.1 | 59.6 | 14-Aug-2010 | |
| LIP6_ranking [?] | 50.7 | 78.8 | 51.3 | 46.1 | 58.2 | 19.5 | 68.6 | 55.6 | 59.5 | 46.8 | 30.7 | 36.0 | 49.3 | 52.3 | 60.0 | 76.4 | 17.8 | 49.1 | 35.3 | 66.3 | 56.6 | 14-Aug-2010 | |
| SPM-SC-HOG [?] | 46.6 | 79.6 | 47.0 | 42.9 | 52.3 | 21.3 | 66.6 | 50.1 | 58.8 | 44.3 | 21.8 | 32.7 | 46.0 | 49.7 | 51.7 | 72.4 | 13.2 | 44.1 | 28.1 | 61.5 | 48.8 | 24-Aug-2010 | |
| WLU-SPM-EMDIST [?] | 46.1 | 75.8 | 49.0 | 36.8 | 44.3 | 21.2 | 65.8 | 52.1 | 52.1 | 45.4 | 28.2 | 35.0 | 45.3 | 47.8 | 54.2 | 71.0 | 14.7 | 39.8 | 32.8 | 62.2 | 48.0 | 30-Aug-2010 | |
| LINEAR-SPARSE [?] | 44.7 | 77.9 | 44.0 | 37.4 | 48.5 | 19.0 | 63.6 | 49.0 | 51.0 | 45.5 | 27.6 | 32.1 | 41.7 | 46.9 | 49.7 | 68.6 | 13.2 | 40.3 | 30.1 | 61.7 | 46.3 | 30-Aug-2010 | |
| LIG_msvm_fuse_concept [?] | 44.0 | 74.4 | 43.0 | 37.5 | 50.4 | 22.0 | 60.7 | 47.1 | 46.8 | 47.5 | 22.2 | 35.0 | 42.2 | 42.9 | 48.4 | 73.8 | 15.6 | 31.8 | 28.9 | 63.8 | 46.6 | 30-Aug-2010 | |
| SVM-Multi features [?] | 43.3 | 81.1 | 45.3 | 47.3 | 46.3 | 20.1 | 42.3 | 36.4 | 49.1 | 37.5 | 20.6 | 38.5 | 43.8 | 44.9 | 54.4 | 68.6 | 18.0 | 48.2 | 26.0 | 57.7 | 40.3 | 25-Aug-2010 | |
| LPbeta-Multi features [?] | 42.6 | 82.1 | 38.6 | 39.5 | 46.5 | 15.5 | 55.0 | 46.4 | 46.5 | 39.9 | 21.3 | 31.2 | 37.6 | 45.8 | 41.4 | 75.5 | 15.7 | 41.7 | 25.0 | 62.5 | 44.3 | 24-Aug-2010 | |
| SVM-SIFT [?] | 37.7 | 69.3 | 40.3 | 27.3 | 44.1 | 19.5 | 54.1 | 23.9 | 44.4 | 42.9 | 20.3 | 31.1 | 37.5 | 36.6 | 40.5 | 68.8 | 9.3 | 24.6 | 20.2 | 55.6 | 43.9 | 30-Aug-2010 | |
| ProtoLearn [?] | 27.0 | 60.7 | 22.1 | 22.7 | 29.0 | 15.0 | 34.9 | 27.8 | 31.6 | 31.9 | 14.1 | 17.4 | 28.9 | 24.0 | 20.6 | 55.8 | 9.2 | 22.0 | 16.8 | 30.9 | 24.6 | 17-Aug-2010 |
Abbreviations
| Title | Method | Affiliation | Contributors | Description | Date |
|---|---|---|---|---|---|
| Best Window + New Colour SIFT | BW+New Colour SIFT | UvA | Jasper Uijlings Koen van de Sande Theo Gevers Arnold Smeulders | Best Window approach with new Colour SIFT trained with Multiple Kernel Learning SVM. | 2010-08-30 18:00:57 |
| BW+New Colour SIFT-SRKDA | BW+New Colour SIFT-SRKDA | University of Amsterdam | Jasper Uijlings Koen van de Sande Theo Gevers Arnold Smeulders Remko Scha | Best Window Approach plus new color sift. Classification by SRKDA | 2010-08-30 23:21:34 |
| FG Detection, FG Tiling | Bonn_FGT_Segm | Univeristy of Bonn | João Carreira, Adrian Ion, Fuxin Li, Cristian Sminchisescu | - Detection on figure-ground segmentations; - Classification by detection; - Semantic segmentation on figure-ground tilings; | 2010-08-30 23:08:18 |
| Bag-of-words with Non-linear SVM | CVC_Flat | Computer Vision Center Barcelona | Fahad Shahbaz Khan Joost van de Weijer Andrew D. Bagdanov Noha Elfiky David Rojas Pep Gonfaus Jordi Gonzalez Maria Vanrell | We followed the standard bag-of-words pipeline with multiple detectors alongwith SIFT, ColorNames and HUE descriptors. To combine Color and SHape, we use our own Color Attention Algorithm. GIST descriptor is used to obtain the holistic representation of an image. Finally, we use a standard Non linear SVM for learning. | 2010-08-30 20:02:47 |
| Bag-of-words with Non-linear SVM | CVC_Plus | Computer Vision Center Barcelona | Fahad Shahbaz Khan Joost van de Weijer Andrew D. Bagdanov Noha Elfiky David Rojas Pep Gonfaus Jordi Gonzalez Maria Vanrell | All of CVC_Flat with additional color features combined through averaging the kernel combinations. | 2010-08-30 22:50:39 |
| CVC_Plus submission combined with Detection result | CVC_Plus_Det | Computer Vision Center Barcelona | Fahad Shahbaz Khan Joost van de Weijer Andrew D. Bagdanov Noha Elfiky David Rojas Pep Gonfaus Jordi Gonzalez Maria Vanrell | Same as our CVC_Plus Submission combined with object localization scores. | 2010-08-30 20:25:29 |
| classifier based on exclusive dense graph | Exclusive-Classifier | National University of Singapore; Panasonic Singapore Laboratories; | Chen Xiangyu, Chen Qiang, Yuan Xiaotong, Song Zheng, Liu Si, Hua Yang, Huang Zhongyang, Shen Shengmei, Yan Shuicheng. | Exclusive calssifier with both visual features and exclusive contextual information. Trained on full train+val set using both visual and context information. | 2010-08-30 19:39:20 |
| SVM kernel fusion with several SIFT | FU-SVM-SIFT | Brno University of Technology | Michal Hradiš, Ivo ?ezní?ek, David Ba?ina, AdamVl?ek | Features: grayscale SIFT and color SIFT Sampling: dense, Harris-Laplace Codebook: k-means 4k BOW trans.: codeword uncertainty - whole image, three horizontal stripes, 2x2 grid Kernel: exp() of weigted X2 distances (fusion of 30 distances) SVM: libsvm | 2010-08-30 13:41:52 |
| Linear SVM on Improved Fisher vector | Improved Fisher Vector | XRCE | Florent Perronnin Jorge Sanchez Thomas Mensink | Based on [PSM10]: F. Perronnin, J. Sanchez and T. Mensink, "Improving the Fisher kernel for Large-Scale Image Classification", ECCV, 2010. | 2010-08-10 07:50:41 |
| kernel regression for all methods | KernelRegFusing | National University of Singapore; Panasonic Singapore Laboratories; | Chen Qiang, Song Zheng, Liu Si, Chen Xiangyu, Hua Yang, Huang Zhongyang, Shen Shengmei, Yan Shuicheng. | kernel regression as a combination method to fuse all other submissions. | 2010-08-30 21:45:24 |
| kernel regression for all methods | KernelRegFusing | National University of Singapore; Panasonic Singapore Laboratories; | Chen Qiang, Song Zheng, Liu Si, Chen Xiangyu, Hua Yang, Huang Zhongyang, Shen Shengmei, Yan Shuicheng. | kernel regression as a combination method to fuse all other submissions. | 2010-08-30 16:43:52 |
| Fusion of MSVMs with several features, concept opt | LIG_msvm_fuse_concept | Laboratoire d'Informatique de Grenoble | Bahjat Safadi Georges Quénot | Late fusion of multiple SVMs with multiple features. features include dense and Harris-Laplace filtered opponent SIFT, color histograms and Gabor transforms. Fusion is optimized by concept. | 2010-08-30 10:06:59 |
| Linear SVM with spatial max pooling features. | LINEAR-SPARSE | NTHU | Tao Yen Tang, Jyun Yi Lin, Cheng Hao Kung, Meng Hua Wu, Chun Han Chien, Jia Yu Kuo, Hwann Tzong Chen | LIBLINEAR with spatial max pooling of sparse features. Sparse featues are determined by ScSPM and color descriptor. Sparse coding dictionary is learned by SPAMS. | 2010-08-30 08:41:08 |
| Baseline with BOF, SPM and gaussian SVM | LIP6_KSVM_Baseline | LIP6 UPMC | David Picard, Nicolas Thome, Matthieu Cord | Baseline with Bag Of Feature scheme, Spatial Pyramid and gaussian SVM | 2010-08-14 16:52:57 |
| l1-MKL with sift, texture and color features | LIP6_MKL_L1 | LIP6 UPMC | David Picard, Nicolas Thome, Matthieu Cord | l1-MKL with sift, texture (gabor) and color features. | 2010-08-24 15:39:16 |
| BOF scheme with ranking classifier | LIP6_ranking | LIP6 UPMC | David Picard, Nicolas Thome, Matthieu Cord | Same as baseline, but with ranking classifier | 2010-08-14 16:54:36 |
| MKL classifier with multiple features | LIRIS_Multi-Feature_MKL_trainval | LIRIS, Ecole Centrale Lyon, CNRS, UMR5205, France | Chao ZHU, Huanzhang FU, Charles-Edmond BICHOT, Emmanuel Dellandrea, Liming CHEN | Multiple Kernel Learning (MKL) classifier with multiple features: colorSIFT (dense+harris-laplace), colorLBP (see our paper in ICPR2010), PHOG, Self-Similarity, and Color Histogram. A vocabulary of 4000 codewords is created for SIFT. Spatial pyramid information is used. Trained on 'train + val' set. | 2010-08-28 21:50:52 |
| LPbeta with multi features | LPbeta-Multi features | Beijing University of Posts and Telecommunications | Cheng Lin, Qi Xianbiao, Li Chunguang, Guo Jun, Zhang Honggang, Chen Guang | LPbeta with multi features including SIFT-gray, SIFT-color and SSIM.Trained on full train+val set with default parameters. | 2010-08-24 12:04:05 |
| SVM with multifeature and detection kernel | MFDETSVM | National University of Singapore; Panasonic Singapore Laboratories; | Chen Qiang, Song Zheng, Liu Si, Hua Yang, Huang Zhongyang, Shen Shengmei, Yan Shuicheng. | SVM classifier with multiple feature and detection kernel. | 2010-08-30 16:39:03 |
| Mulitkernel fusion with KDA | Multikernel+KDA | The University of Surrey | Piotr Koniusz, Muhammad Atif Tahir, Mark Barnard, Fei Yan, Krystian Mikolajczyk | Kernel-level fusion with Spatial Pyramid Grids, Soft Assignment and Kernel Discriminant Analysis using spectral regression. 18 kernels have been generated from 18 variants of SIFT. | 2010-08-30 01:48:44 |
| Saliency coding and dictionary learning | NLPR_VSTAR_CLS_DICTLEARN | National Laboratory of Pattern Recognition , Institute of Automation, Chinese Academy of Sciences | tntgroup | Lib-SVM classifier with dense SIFT features, saliency coding, dictionary leanring and detection information. | 2010-08-30 19:50:42 |
| Learning the prototype of image categories | ProtoLearn | Harbin Institute of Technology | Deyuan Zhang Bingquan Liu Chengjie Sun XIaolong Wang | Dense SIFT features, learning the prototype of images using large margin framework. Trains the classifier using 200 positive and 300 negative images selected randomly. The parameters is fixed. | 2010-08-17 15:06:46 |
| SVM Classifier with dense and Harris BOF | Ritsu_CBVR_WKF | Ritsumeikan University | Xian-Hua Han, Yen-Wei Chen, Xiang Ruan | We extracted Gray and color (Opponent and C_sift) BOF feature with dense and Harris sampling, and use SVM with normalized kernel fusion for classification | 2010-08-30 02:45:21 |
| Multiple kernel learning with SIFT GMMs | SIFT-GMM-MKL | Tokyo Institute of Technology | Nakamasa Inoue, Yusuke Kamishima, Koichi Shinoda | We use multiple kernel learning and GMM supervector kernels with SIFT features. | 2010-08-30 04:39:41 |
| Linear SVM Classifier with dense HOG features | SPM-SC-HOG | Beijing University of Posts and Telecommunications | Qi Xianbiao, Cheng Lin, Li Chunguang, Guo Jun, Zhang Honggang, Chen Guang | Liblinear classifier with dense HOG features. Trained on full train+val set with default parameters. | 2010-08-24 12:26:56 |
| Svm classifier with multi features | SVM-Multi features | Beijing University of Posts and Telecommunications | Cheng Lin, Qi Xianbiao, Li Chunguang, Guo Jun, Zhang Honggang, Chen Guang | Libsvm classifier with multi features. Re-trained the final result with default cross-validation and tuned parameters. | 2010-08-25 13:59:28 |
| SVM classifier with color sift features | SVM-SIFT | NII | Xiao Zhou ?Cai-Zhi Zhu | libsvm classifier with color sift features. Trained using 5-fold cross-validation. Re-trained on val set with fixed parameters. | 2010-08-30 22:46:05 |
| SVM classifier on PMK and SPMK approaches with lin | SVM_LDP_SIFT_PMK_SPMK | National University of Defense Technology | Hongping Cai, Krystian Mikolajczk, Dewen Hu | Local features are extracted on regular grids at multiple scales, then described by SIFT and 'SIFT+hue histogram'. To reduce the memory and computational cost, the linear discriminant projection (LDP) are applied, leading to significant feature dimensionality reduction and performance boosting. With the 30-dim LDP-projected features, the submitted results are obtained by fusing pyramid match kernel (PMK) and spatial pyramid match kernel (SPMK), with an SVM classifier for the final stage. | 2010-08-25 05:33:25 |
| SVM classifier on low-level modeling based approac | SVM_WHGO_SIFT_CENTRIST_low-level modeling | Department of Automatic Control, College of Mechatronics and Automation, National University of Defense Technology | Li Zhou, Zongtan Zhou, Dewen Hu | This method is based on a low-level modeling strategy. The approach works by creating multiple resolution images and partitioning them into sub-regions at different scales. We represent each sub-region with WHGO, CENTRIST and SIFT descriptors and combine the features of different descriptor and resolution channels through an SVM classifier to form the final decision function. | 2010-08-23 06:02:40 |
| Combination of Generative Discriminative Methods | UC3M_Generative_Discriminative | Universidad Carlos III de Madrid | Iván González-Díaz, Fernando Díaz de María | Combination of Supervised Topic Models with SVM-based discriminative methods for concurrent image recognition and segmentation | 2010-08-30 13:27:41 |
| SPM/lin.SVM, codebook using Earth Mover dist. | WLU-SPM-EMDIST | Washington and Lee University | Chen Zhong, William Richardson, Joshua Stough | Spatial Pyramid Match after Lazebnik. Linear SVM on LLC-coded dense SIFT features after Yang/Wang/Yu. Annotation-based codebook training. SPM levels trained separately and combined. Codebook generated using Earth Mover's distance. | 2010-08-30 21:03:29 |
| v1_classdependent_nodection | hog, lbp, nonlinear coding, svm | NEC Labs, America | NEC: Yuanqing Lin, Fengjun Lv, Shenghuo Zhu, Ming Yang, Timothee Cour, Kai Yu UIUC: LiangLiang Cao, Thomas Huang Rutgers Univ.: Tong Zhang Univ. Missouri: Xiaoyu Wang, Tony Xu Han | Dense DHOG and LBP features are coded by both local linear and nonlinear methods. The resulting high-dimension features were then fed to linear SVMs. Class dependent cross-validation. | 2010-08-30 22:45:36 |
| v1_classdependent_withdetection | hog, lbp, nonlinear coding, svm, detection | NEC Labs, America | NEC: Yuanqing Lin, Fengjun Lv, Shenghuo Zhu, Ming Yang, Timothee Cour, Kai Yu UIUC: LiangLiang Cao, Thomas Huang Rutgers Univ.: Tong Zhang Univ. Missouri: Xiaoyu Wang, Tony Xu Han | Dense DHOG and LBP features are coded by both local linear and nonlinear methods. The resulting high-dimension features were then fed to linear SVMs. Detection results were taken into account. Class dependent cross-validation. | 2010-08-30 22:49:49 |