Columbia University/VIREO-CityU/IRIT

 A_CU-run6: local feature alone – average fusion of 3 SVM classification results for each concept using various feature representation choices.  A_CU-run5: linear weighted fusion of A_CU-run6 with two grid-based global features (color moment and wavelet texture).  A_CU-run4: linear weighted fusion of A_CU-run5 with a SVM classification result using detection scores of CU-VIREO374 as features.  C_CU-run3: linear weighted fusion of A_CU-run4 with a SVM classification result using web images.  A_CU-run2: re-rank the results of “two_people” and “singing” from A_CU-run4 with concept-specific detectors.  C_CU-run1: linear weighted fusion of A_CU-run2 with a SVM classification result using web images.