Home /
Research
Showing 511 - 516 / 897
Learn an Effective Lip Reading Model without Pains
DaluFeng, ShuangYang, ShiguangShan....
Published date-11/15/2020
Lipreading, LipReading, SpeechRecognition, VisualSpeechRecognition
Lip reading, also known as visual speech recognition, aims to recognize the speech content from videos by analyzing the lip dynamics. There have been several appealing progress in recent years, …
Unsupervised Contrastive Learning of Sound Event Representations
EduardoFonseca, DiegoOrtego, KevinMcGuinness....
Published date-11/15/2020
ContrastiveLearning, RepresentationLearning
Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore …
TenFor: A Tensor-Based Tool to Extract Interesting Events from Security Forums
RisulIslam, MdOmarFarukRokon, EvangelosE.Papalexakis....
Published date-11/14/2020
Clustering
How can we get a security forum to "tell" us its activities and events of interest? We take a unique angle: we want to identify these activities without any a …
CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection
SeverinLaicher, GioiaBaldissin, EnriqueCastañeda....
Published date-11/14/2020
We present the results of our participation in the DIACR-Ita shared task on lexical semantic change detection for Italian. We exploit Average Pairwise Distance of token-based BERT embeddings between time …
Self Normalizing Flows
T.AndersonKeller, JornW.T.Peters, PriyankJaini....
Published date-11/14/2020
Efficient gradient computation of the Jacobian determinant term is a core problem of the normalizing flow framework. Thus, most proposed flow models either restrict to a function class with easy …
Opponent Learning Awareness and Modelling in Multi-Objective Normal Form Games
RoxanaRădulescu, TimothyVerstraeten, YijieZhang....
Published date-11/14/2020
Many real-world multi-agent interactions consider multiple distinct criteria, i.e. the payoffs are multi-objective in nature. However, the same multi-objective payoff vector may lead to different utilities for each participant. Therefore, …