Factorizing appearance using epitomic flobject analysis

Previously, `flobject analysis´ was introduced as a method for using motion or stereo disparity information to train better models of static images. During training, but not during testing, optic flow is used as a cue for factorizing appearance-based image features into those belonging to different flow-defined objects, or flobjects. Here, we describe how the image epitome can be extended to model flobjects and introduce a suitable learning algorithm. Using the CityCars and City F´edestrians datasets, we study the tasks of object classification and localization. Our method performs significantly better than the original LDA-based flobject analysis technique, SIFT-based methods with and without spatial pyramid matching, and gist descriptors.