Real-Time Bag of Words, Approximately
We start from the state-of-the-art Bag of Words pipeline that in the 2008 benchmarks of TRECvid and PASCAL yielded the best performance scores. We have contributed to that pipeline, which now forms the basis to compare var- ious fast alternatives for all of its components: (i) For de scriptor extraction we propose a fast algorithm to densely sample SIFT and SURF, and we compare several variants of these descriptors. (ii) For descriptor projection we com- pare a k-means visual vocabulary with a Random Forest. As a preprojection step we experiment with PCA on the descriptors to decrease projection time. (iii) For classification we use Support Vector Machines and compare the 2 kernel with the RBF kernel. Our results lead to a 10-fold speed increase without any loss of accuracy and to a 30-fold speed increase with 17% loss of accuracy, where the latter system does real-time classification at 26 images per second.