This paper presents a novel design of content fingerprints based on maximization of the mutual information across the distortion channel. We use the information bottleneck method to optimize the filters and quantizers that generate these fingerprints. A greedy optimization scheme is used to select filters from a dictionary and allocate fingerprint bits. We test the performance of this method for a...Show More
Viewpoint-invariant object matching is challenging due to image distortions caused by several factors such as rotation, translation, illumination, cropping and occlusion. We propose a compact, global image descriptor for Manhattan scenes that captures relative locations and strengths of edges along vanishing directions. To construct the descriptor, an edge map is determined per vanishing point, ca...Show More
This paper proposes a machine learning method based on Real Adaboost that jointly optimizes the content ID codes and the decoding metric. Significant performance gains over prior art are demonstrated for audio fingerprinting.Show More
In this paper, decoding metrics are designed for statistical fingerprint-based content identification. A fairly general class of structured codes is considered, and a statistical model for the resulting fingerprints and their degraded versions (following miscellaneous content distortions) is proposed and validated. The Maximum-Likelihood fingerprint decoder derived from this model is shown to cons...Show More
Adhoc Network nodes engage in localized grouping and organization based on their neighbourhood to carry out complex goals such as end to end communication. Certain network nodes are enlisted as localized relays to assist in passing messages along a chain. This paper proposes a method to exploit the presence of relay nodes in wireless networks to mitigate interference from other simultaneous transm...Show More
