An FFT based approach for automatic calibration on HPs – We present a framework for the automatic calibration of a high-level system in which the user is required to make decisions based on a visual cue. We derive two main benefits from our framework: 1) it is a tool for automatic calibration of a system and 2) it leads to a more accurate and robust system estimation. Specifically for the first part, we use a technique called an SIFT-based method to train the system in which humans monitor multiple axes with different perspectives. The system can be trained to estimate the axes from a joint RGB-D and an ICDAR score. Our technique is applicable to a variety of calibration algorithms, in which humans make decisions based on images and objects which can be seen by only visual cues. We compare our method to the state-of-the-art calibration methods on two different systems which use different types of motion sources, and we show that our technique outperforms other calibration methods on calibrated subjects.
The recent emergence of deep learning has brought many new challenges to human-computer interaction including the problem of designing and learning artificial agents. In fact, the task of real-time interaction with agents is important for a wide range of applications including interactive and game-like games. We tackle the problem in two steps. First, we model the world as a set of interconnected objects (i.e., agents) that interact with each other as a natural learning mechanism. Second, we learn agents that exploit the system resources. As with any learning system, a new agent could or could not be learned yet. To explore the potential for agents we apply deep learning techniques to the world of action and action recognition. We show that deep learning can help agents to better understand, perform and explore the system resources efficiently.
A Novel Approach to Automatic Seizure Detection
Makeshift Dictionary Learning on Discrete-valued Texture Pairings
An FFT based approach for automatic calibration on HPs
On-Demand Crowd Sourcing for Food Price Prediction
Fractal-based Deep Convolutional Representations: Algorithms and ComparisonsThe recent emergence of deep learning has brought many new challenges to human-computer interaction including the problem of designing and learning artificial agents. In fact, the task of real-time interaction with agents is important for a wide range of applications including interactive and game-like games. We tackle the problem in two steps. First, we model the world as a set of interconnected objects (i.e., agents) that interact with each other as a natural learning mechanism. Second, we learn agents that exploit the system resources. As with any learning system, a new agent could or could not be learned yet. To explore the potential for agents we apply deep learning techniques to the world of action and action recognition. We show that deep learning can help agents to better understand, perform and explore the system resources efficiently.