Abstract
We propose a novel approach to boost the performance of generic object detectors on videos by learning videospecifific features using a deep neural network. The insight behind our proposed approach is that an object appearing in different frames of a video clip should share similar features, which can be learned to build better detectors. Unlike many supervised detector adaptation or detection-bytracking methods, our method does not require any extra annotations or utilize temporal correspondence. We start with the high-confifidence detections from a generic detector, then iteratively learn new video-specifific features and refifine the detection scores. In order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders. It differs from the existing unsupervised feature learning methods in two ways: fifirst it optimizes both discriminative and generative properties of the features simultaneously, which gives our features better discriminative ability; second, our learned features are more compact, while the unsupervised feature learning methods usually learn a redundant set of over-complete features. Extensive experimental results on person and horse detection show that signifificant performance improvement can be achieved with our proposed method.