Home /

Research

Showing 625 - 630 / 897

Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation


Authors:  AngelMartínez-González, MichaelVillamizar, OlivierCanévet....
Published date-11/10/2020
Tasks:  3DHumanPoseEstimation, 3DPoseEstimation, Humanrobotinteraction, PoseEstimation

Abstract: We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person Human-Robot Interaction …

Building an Automated and Self-Aware Anomaly Detection System


Authors:  SayanChakraborty, SmitShah, KiumarsSoltani....
Published date-11/10/2020
Tasks:  AnomalyDetection, TimeSeries

Abstract: Organizations rely heavily on time series metrics to measure and model key aspects of operational and business performance. The ability to reliably detect issues with these metrics is imperative to …

Two-Sided Fairness in Non-Personalised Recommendations


Authors:  AadiSwadiptoMondal, RakeshBal, SayanSinha....
Published date-11/10/2020
Tasks:  fairness, RecommendationSystems

Abstract: Recommender systems are one of the most widely used services on several online platforms to suggest potential items to the end-users. These services often use different machine learning techniques for …

Efficient and Transferable Adversarial Examples from Bayesian Neural Networks


Authors:  MartinGubri, MaximeCordy, MikePapadakis....
Published date-11/10/2020

Abstract: Deep neural networks are vulnerable to evasion attacks, i.e., carefully crafted examples designed to fool a model at test time. Attacks that successfully evade an ensemble of models can transfer …

What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes


Authors:  HermanYau, ChrisRussell, SimonHadfield....
Published date-11/10/2020

Abstract: We present a novel form of explanation for Reinforcement Learning, based around the notion of intended outcome. These explanations describe the outcome an agent is trying to achieve by its …

Towards a Better Global Loss Landscape of GANs


Authors:  RuoyuSun, TiantianFang, AlexSchwing....
Published date-11/10/2020

Abstract: Understanding of GAN training is still very limited. One major challenge is its non-convex-non-concave min-max objective, which may lead to sub-optimal local minima. In this work, we perform a global …

Filter by

Categories

Tags