Home /

Research

Showing 697 - 702 / 897

Right on Time: Multi-Temporal Convolutions for Human Action Recognition in Videos


Authors:  AlexandrosStergiou, RonaldPoppe....
Published date-11/08/2020
Tasks:  ActionRecognition, ActionRecognitionInVideos, ActionRecognitionInVideos, TemporalActionLocalization, TransferLearning

Abstract: The variations in the temporal performance of human actions observed in videos present challenges for their extraction using fixed-sized convolution kernels in CNNs. We present an approach that is more …

Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification


Authors:  AgusSudjianto, WilliamKnauth, RahulSingh....
Published date-11/08/2020

Abstract: The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box" models without a sufficient …

Pathwise Conditioning of Gaussian Processes


Authors:  JamesT.Wilson, ViacheslavBorovitskiy, AlexanderTerenin....
Published date-11/08/2020
Tasks:  GaussianProcesses

Abstract: As Gaussian processes are integrated into increasingly complex problem settings, analytic solutions to quantities of interest become scarcer and scarcer. Monte Carlo methods act as a convenient bridge for connecting …

Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers


Authors:  ShucongZhang, ErfanLoweimi, PeterBell....
Published date-11/08/2020
Tasks:  SpeechRecognition

Abstract: Recently, Transformers have shown competitive automatic speech recognition (ASR) results. One key factor to the success of these models is the multi-head attention mechanism. However, we observed in trained models, …

Adaptive Linear Span Network for Object Skeleton Detection


Authors:  ChangLiu, YunjieTian, JianbinJiao....
Published date-11/08/2020
Tasks:  EdgeDetection, NeuralArchitectureSearch, ObjectSkeletonDetection

Abstract: Conventional networks for object skeleton detection are usually hand-crafted. Although effective, they require intensive priori knowledge to configure representative features for objects in different scale granularity.In this paper, we propose …

Adapting a Language Model for Controlled Affective Text Generation


Authors:  IshikaSingh, AhsanBarkati, TusharGoswamy....
Published date-11/08/2020
Tasks:  LanguageModelling, TextGeneration

Abstract: Human use language not just to convey information but also to express their inner feelings and mental states. In this work, we adapt the state-of-the-art language generation models to generate …

Filter by

Categories

Tags