Video Highlights and Video Statistics in First Place – Automatically identifying keypoints is a challenging problem in data mining. Recent work has shown that finding the most important keypoints is a multi-step problem, which has led to many successful research efforts. However, keypoints are commonly not detected automatically after an important step in a system architecture. This paper presents an algorithm for identifying keypoints with high probability. The algorithm is an extension of the traditional one-step learning algorithms. It aims to find keypoints that lie in a global proximity in data. We present an algorithm for the identification of keypoints with high probability. We first show how to identify keypoints that lie in a global proximity using a sparse metric, and then propose a variant of the algorithm that can be used to find keypoint locations. The algorithm is evaluated on the problem of finding the most important keypoints by means of a simple and fast algorithm. Experimental results show that our algorithm outperforms other related keypoint mining algorithms.

Person recognition is a vital task in many computer-based applications, but human performance is typically too poor to be considered a benchmark. However, it’s very important to consider the role of the human to make the decisions regarding what person to recognize. This paper presents a novel approach for face recognition in action videos, which is based on a deep network. The network is trained for a multi-dimensional space (with both a facial and a visual input), which is capable to capture the human’s face attributes. Experiments show that the proposed model is capable of recognising human expressions (including the facial-expression similarity level) of human. Moreover, it makes it possible to identify people that have been described as being similar to the human. Therefore, the proposed approach may be useful to users of action-based video games.

Learning Topic Models by Unifying Stochastic Convex Optimization and Nonconvex Learning

On the Impact of Negative Link Disambiguation of Link Profiles in Text Streams

Video Highlights and Video Statistics in First Place

Predicting the Parameters of EHRs with Deep Learning

Generating a Robust Multimodal Corpus for Robust Speech RecognitionPerson recognition is a vital task in many computer-based applications, but human performance is typically too poor to be considered a benchmark. However, it’s very important to consider the role of the human to make the decisions regarding what person to recognize. This paper presents a novel approach for face recognition in action videos, which is based on a deep network. The network is trained for a multi-dimensional space (with both a facial and a visual input), which is capable to capture the human’s face attributes. Experiments show that the proposed model is capable of recognising human expressions (including the facial-expression similarity level) of human. Moreover, it makes it possible to identify people that have been described as being similar to the human. Therefore, the proposed approach may be useful to users of action-based video games.