Niels Haering Niels da Vitoria Lobo Richard J. Qian M. Ibrahim Sezan University of Central Florida Sharp Labs of America Orlando, FL 32816 Camas, WA 98607 Abstract We propose a three-level algorithm for the design of event detectors. The rst level extracts texture, color and motion features, and detects motion blobs. The mid-level employs a neural network to verify the relevance of the detected...

This paper presents a study of employing Ranking SVM and Convolutional Neural Network for two missions: legal information retrieval and question answering in the Competition on Legal Information Extraction/Entailment. For the first task, our proposed model used a triple of features (LSI, Manhattan, Jaccard), and is based on paragraph level instead of article level as in previous studies. In fac...

Significant research has gone into engineering representations that can identify high-level semantic structure in images, such as objects, people, events and scenes. Recently there has been a shift towards learning representations of images either on top of dense features or directly from the pixel level. These features are often learned in hierarchies using large amounts of unlabeled data with...

Gestures are a natural and effective altenative to command mobile robots. This paper describes an online visual recognition system to recognize a set of 5 dynamic gestures executed with the user’s right hand and oriented to command mobile robots. The system employs a radial scan segmentation algorithm combined with a statistical-based skin detection method to find the candidate face of the user...

Deep convolutional neural networks follow roughly the architecture of biological visual systems, and have shown a performance comparable to human observers in object recognition tasks. In this study, I test a pretrained deep neural network in some classic visual search tasks. The results reveal a qualitative difference from human performance. It appears that there is no difference between searc...