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.Entries equivalent to a selected submission are determined by bootstrapping the performance measure, and assessing if the differences between the selected submission and the others are not statistically significant (see sec 3.5 in VOC 2014 paper).

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 [?] 73.893.079.071.677.854.385.278.678.864.564.062.769.682.084.591.648.664.959.789.476.430-Aug-2010
KernelRegFusing [?] 73.792.879.270.978.154.285.278.978.564.464.563.268.781.684.591.348.465.059.589.376.030-Aug-2010
NLPR_VSTAR_CLS_DICTLEARN [?] 71.290.377.065.375.053.785.980.574.662.966.254.166.876.181.789.941.666.357.085.074.330-Aug-2010
MFDETSVM [?] 72.191.977.169.574.752.584.377.376.263.063.562.965.079.583.291.245.565.455.087.077.230-Aug-2010
Exclusive-Classifier [?] 71.591.377.170.075.650.783.277.175.462.562.662.764.677.981.891.144.864.353.286.377.130-Aug-2010
BW+New Colour SIFT-SRKDA [?] 69.090.666.963.470.249.481.976.771.060.057.160.564.567.479.190.253.363.558.081.974.430-Aug-2010
CVC_Plus_Det [?] 67.891.770.066.871.349.181.477.571.260.052.655.761.070.976.788.443.259.753.884.771.330-Aug-2010
hog, lbp, nonlinear coding, svm, detection [?] 70.993.373.069.977.247.985.779.779.461.756.661.171.176.779.386.838.163.955.887.572.930-Aug-2010
BW+New Colour SIFT [?] 69.391.571.067.370.043.980.675.373.459.357.860.864.070.680.088.650.965.656.183.076.230-Aug-2010
hog, lbp, nonlinear coding, svm [?] 69.693.371.769.976.942.085.377.479.460.055.960.671.175.777.786.833.561.555.887.569.930-Aug-2010
CVC_Plus [?] 64.491.061.866.771.137.778.967.872.255.851.055.859.465.373.084.039.956.948.583.968.130-Aug-2010
FU-SVM-SIFT [?] 63.989.763.964.568.336.877.968.572.057.247.256.763.566.874.285.032.854.349.182.666.830-Aug-2010
Multikernel+KDA [?] 66.590.666.167.270.636.079.769.873.458.450.760.165.269.876.987.042.559.649.985.271.330-Aug-2010
Bonn_FGT_Segm [?] 61.488.061.653.163.334.877.572.371.141.156.039.764.468.975.487.532.559.340.878.861.430-Aug-2010
SIFT-GMM-MKL [?] 58.987.256.659.666.032.672.763.164.854.641.249.358.859.168.282.931.249.243.275.063.430-Aug-2010
CVC_Flat [?] 61.189.457.663.068.532.076.764.766.951.548.450.054.863.169.983.533.754.846.182.265.930-Aug-2010
Improved Fisher Vector [?] 61.287.159.659.969.731.376.462.964.352.542.455.159.764.370.483.932.653.350.480.067.610-Aug-2010
LIRIS_Multi-Feature_MKL_trainval [?] 60.087.557.061.768.329.976.661.967.556.935.150.655.162.269.383.635.952.942.879.866.328-Aug-2010
Ritsu_CBVR_WKF [?] 57.485.657.254.964.529.271.257.163.253.937.649.654.758.767.980.129.252.243.576.460.930-Aug-2010
SVM_LDP_SIFT_PMK_SPMK [?] 56.486.159.360.268.728.774.863.568.052.541.447.157.560.968.281.529.452.144.579.14.725-Aug-2010
SVM_WHGO_SIFT_CENTRIST_low-level modeling [?] 57.183.554.255.266.828.572.165.464.251.936.149.355.658.066.582.125.348.141.778.459.523-Aug-2010
UC3M_Generative_Discriminative [?] 57.185.551.655.464.825.974.460.666.051.045.943.955.059.065.280.324.151.447.076.458.630-Aug-2010
LIP6_MKL_L1 [?] 55.578.555.954.662.525.069.359.560.051.337.946.754.060.564.072.832.852.638.572.761.124-Aug-2010
LIP6_KSVM_Baseline [?] 54.278.554.149.961.124.768.358.059.950.735.742.655.060.963.171.125.951.539.974.159.614-Aug-2010
LIG_msvm_fuse_concept [?] 44.074.443.037.550.422.060.747.146.847.522.235.042.242.948.473.815.631.828.963.846.630-Aug-2010
SPM-SC-HOG [?] 46.679.647.042.952.321.366.650.158.844.321.832.746.049.751.772.413.244.128.161.548.824-Aug-2010
WLU-SPM-EMDIST [?] 46.175.849.036.844.321.265.852.152.145.428.235.045.347.854.271.014.739.832.862.248.030-Aug-2010
SVM-Multi features [?] 43.381.145.347.346.320.142.336.449.137.520.638.543.844.954.468.618.048.226.057.740.325-Aug-2010
SVM-SIFT [?] 37.769.340.327.344.119.554.123.944.442.920.331.137.536.640.568.89.324.620.255.643.930-Aug-2010
LIP6_ranking [?] 50.778.851.346.158.219.568.655.659.546.830.736.049.352.360.076.417.849.135.366.356.614-Aug-2010
LINEAR-SPARSE [?] 44.777.944.037.448.519.063.649.051.045.527.632.141.746.949.768.613.240.330.161.746.330-Aug-2010
LPbeta-Multi features [?] 42.682.138.639.546.515.555.046.446.539.921.331.237.645.841.475.515.741.725.062.544.324-Aug-2010
ProtoLearn [?] 27.060.722.122.729.015.034.927.831.631.914.117.428.924.020.655.89.222.016.830.924.617-Aug-2010

Abbreviations

TitleMethodAffiliationContributorsDescriptionDate
Best Window + New Colour SIFTBW+New Colour SIFTUvAJasper Uijlings Koen van de Sande Theo Gevers Arnold SmeuldersBest Window approach with new Colour SIFT trained with Multiple Kernel Learning SVM.2010-08-30 18:00:57
BW+New Colour SIFT-SRKDABW+New Colour SIFT-SRKDAUniversity of AmsterdamJasper Uijlings Koen van de Sande Theo Gevers Arnold Smeulders Remko SchaBest Window Approach plus new color sift. Classification by SRKDA2010-08-30 23:21:34
FG Detection, FG TilingBonn_FGT_SegmUniveristy of BonnJoão 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 SVMCVC_FlatComputer Vision Center BarcelonaFahad Shahbaz Khan Joost van de Weijer Andrew D. Bagdanov Noha Elfiky David Rojas Pep Gonfaus Jordi Gonzalez Maria VanrellWe 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 SVMCVC_PlusComputer Vision Center BarcelonaFahad Shahbaz Khan Joost van de Weijer Andrew D. Bagdanov Noha Elfiky David Rojas Pep Gonfaus Jordi Gonzalez Maria VanrellAll 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 resultCVC_Plus_DetComputer Vision Center BarcelonaFahad Shahbaz Khan Joost van de Weijer Andrew D. Bagdanov Noha Elfiky David Rojas Pep Gonfaus Jordi Gonzalez Maria VanrellSame as our CVC_Plus Submission combined with object localization scores.2010-08-30 20:25:29
classifier based on exclusive dense graphExclusive-ClassifierNational 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-SIFTBrno University of Technology Michal Hradiš, Ivo ?ezní?ek, David Ba?ina, AdamVl?ekFeatures: 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 vectorImproved Fisher VectorXRCEFlorent Perronnin Jorge Sanchez Thomas MensinkBased 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 methodsKernelRegFusingNational 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 methodsKernelRegFusingNational 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 optLIG_msvm_fuse_conceptLaboratoire d'Informatique de GrenobleBahjat Safadi Georges QuénotLate 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-SPARSENTHUTao Yen Tang, Jyun Yi Lin, Cheng Hao Kung, Meng Hua Wu, Chun Han Chien, Jia Yu Kuo, Hwann Tzong ChenLIBLINEAR 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 SVMLIP6_KSVM_BaselineLIP6 UPMCDavid Picard, Nicolas Thome, Matthieu CordBaseline with Bag Of Feature scheme, Spatial Pyramid and gaussian SVM2010-08-14 16:52:57
l1-MKL with sift, texture and color featuresLIP6_MKL_L1LIP6 UPMCDavid Picard, Nicolas Thome, Matthieu Cordl1-MKL with sift, texture (gabor) and color features.2010-08-24 15:39:16
BOF scheme with ranking classifierLIP6_rankingLIP6 UPMCDavid Picard, Nicolas Thome, Matthieu CordSame as baseline, but with ranking classifier2010-08-14 16:54:36
MKL classifier with multiple featuresLIRIS_Multi-Feature_MKL_trainvalLIRIS, Ecole Centrale Lyon, CNRS, UMR5205, FranceChao ZHU, Huanzhang FU, Charles-Edmond BICHOT, Emmanuel Dellandrea, Liming CHENMultiple 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 featuresLPbeta-Multi featuresBeijing University of Posts and TelecommunicationsCheng Lin, Qi Xianbiao, Li Chunguang, Guo Jun, Zhang Honggang, Chen GuangLPbeta 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 MFDETSVMNational 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 KDAMultikernel+KDA The University of SurreyPiotr Koniusz, Muhammad Atif Tahir, Mark Barnard, Fei Yan, Krystian MikolajczykKernel-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 learningNLPR_VSTAR_CLS_DICTLEARNNational Laboratory of Pattern Recognition , Institute of Automation, Chinese Academy of SciencestntgroupLib-SVM classifier with dense SIFT features, saliency coding, dictionary leanring and detection information.2010-08-30 19:50:42
Learning the prototype of image categoriesProtoLearnHarbin Institute of TechnologyDeyuan Zhang Bingquan Liu Chengjie Sun XIaolong WangDense 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 BOFRitsu_CBVR_WKFRitsumeikan UniversityXian-Hua Han, Yen-Wei Chen, Xiang RuanWe extracted Gray and color (Opponent and C_sift) BOF feature with dense and Harris sampling, and use SVM with normalized kernel fusion for classification2010-08-30 02:45:21
Multiple kernel learning with SIFT GMMsSIFT-GMM-MKL Tokyo Institute of TechnologyNakamasa Inoue, Yusuke Kamishima, Koichi ShinodaWe use multiple kernel learning and GMM supervector kernels with SIFT features.2010-08-30 04:39:41
Linear SVM Classifier with dense HOG featuresSPM-SC-HOGBeijing University of Posts and TelecommunicationsQi Xianbiao, Cheng Lin, Li Chunguang, Guo Jun, Zhang Honggang, Chen GuangLiblinear classifier with dense HOG features. Trained on full train+val set with default parameters.2010-08-24 12:26:56
Svm classifier with multi featuresSVM-Multi featuresBeijing University of Posts and TelecommunicationsCheng Lin, Qi Xianbiao, Li Chunguang, Guo Jun, Zhang Honggang, Chen GuangLibsvm 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 featuresSVM-SIFTNII JapanXiao Zhou ?Cai-Zhi Zhulibsvm 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 linSVM_LDP_SIFT_PMK_SPMKNational University of Defense TechnologyHongping Cai, Krystian Mikolajczk, Dewen HuLocal 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 approacSVM_WHGO_SIFT_CENTRIST_low-level modelingDepartment of Automatic Control, College of Mechatronics and Automation, National University of Defense TechnologyLi Zhou, Zongtan Zhou, Dewen HuThis 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 MethodsUC3M_Generative_DiscriminativeUniversidad Carlos III de MadridIván González-Díaz, Fernando Díaz de MaríaCombination of Supervised Topic Models with SVM-based discriminative methods for concurrent image recognition and segmentation2010-08-30 13:27:41
SPM/lin.SVM, codebook using Earth Mover dist.WLU-SPM-EMDISTWashington and Lee UniversityChen Zhong, William Richardson, Joshua StoughSpatial 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_nodectionhog, lbp, nonlinear coding, svmNEC Labs, AmericaNEC: 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_withdetectionhog, lbp, nonlinear coding, svm, detectionNEC Labs, AmericaNEC: 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