Home /
Research
Showing 751 - 756 / 897
Can Human Sex Be Learned Using Only 2D Body Keypoint Estimations?
KristijanBartol, TomislavPribanic, DavidBojanic....
Published date-11/05/2020
In this paper, we analyze human male and female sex recognition problem and present a fully automated classification system using only 2D keypoints. The keypoints represent human joints. A keypoint …
EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering
MomchilHardalov, TodorMihaylov, DimitrinaZlatkova....
Published date-11/05/2020
QuestionAnswering, TransferLearning
We propose EXAMS -- a new benchmark dataset for cross-lingual and multilingual question answering for high school examinations. We collected more than 24,000 high-quality high school exam questions in 16 …
RealAnt: An Open-Source Low-Cost Quadruped for Research in Real-World Reinforcement Learning
RinuBoney, JussiSainio, MikkoKaivola....
Published date-11/05/2020
Current robot platforms available for research are either very expensive or unable to handle the abuse of exploratory controls in reinforcement learning. We develop RealAnt, a minimal low-cost physical version …
Semi-supervised URL Segmentation with Recurrent Neural NetworksPre-trained on Knowledge Graph Entities
HaoZhang, JaeRo, RichardSproat....
Published date-11/05/2020
ChineseWordSegmentation, SpeechSynthesis, Text-To-SpeechSynthesis
Breaking domain names such as openresearch into component words open and research is important for applications like Text-to-Speech synthesis and web search. We link this problem to the classic problem …
Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping
KhaledKoutini, FlorianHenkel, HamidEghbal-zadeh....
Published date-11/05/2020
AcousticSceneClassification, SceneClassification
Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a …
Learning Efficient Task-Specific Meta-Embeddings with Word Prisms
JingyiHe, KCTsiolis, KianKenyon-Dean....
Published date-11/05/2020
WordEmbeddings
Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. …