Learn More
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discrimina-tive model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task learning problem, our model is able to selectively predict partial poses in the presence of noise and occlusion. Our(More)
We present an attention-based model that reasons on human body shape and motion dynamics to identify individuals in the absence of RGB information, hence in the dark. Our approach leverages unique 4D spatio-temporal signatures to address the identification problem across days. Formulated as a reinforcement learning task, our model is based on a combination(More)
Processing large volumes of RDF data requires sophisticated tools. In recent years, much effort was spent on optimizing native RDF stores and on repurposing relational query engines for large-scale RDF processing. Concurrently, a number of new data management systems— regrouped under the NoSQL (for " not only SQL ") umbrella—rapidly rose to prominence and(More)
Inspired by the recent success of RGB-D cameras, we propose the enrichment of RGB data with an additional "quasi-free" modality, namely, the wireless signal (e.g., wifi or Bluetooth) emitted by individuals' cell phones, referred to as RGB-W. The received signal strength acts as a rough proxy for depth and a reliable cue on their identity. Although the(More)
Acknowledgments First and foremost, I would like to thank Daniel Miranker, my thesis advisor, for his insight and guidance throughout the process of working on this thesis. His mentorship and encouragement were essential in developing this project from idea generation to maturity. I would like to thank all the members of the Research in Bioinformatics and(More)
In this paper, we study a resource allocation problem, specifically allocation of power and rate (modulation order) to secondary users in a competitive cognitive radio network (CRN). In a competitive CRN, multiple secondary users share a single channel and multiple channels are simultaneously used by a single secondary user (SU) to satisfy their rate(More)
Recent progress in developing cost-effective depth sensors has enabled new AI-assisted solutions such as assisted driving vehicles and smart spaces. Machine learning techniques have been successfully applied on these depth signals to perceive meaningful information about human behavior. In this work, we propose to deploy depth sensors in hospital settings(More)