Home /

Research

Showing 139 - 144 / 897

Counting People by Estimating People Flows


Authors:  WeizheLiu, MathieuSalzmann, PascalFua....
Published date-12/01/2020
Tasks:  ActiveLearning, CrowdCounting, OpticalFlowEstimation

Abstract: Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in …

Fully Convolutional Networks for Panoptic Segmentation


Authors:  YanweiLi, HengshuangZhao, XiaojuanQi....
Published date-12/01/2020
Tasks:  PanopticSegmentation

Abstract: In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff …

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design


Authors:  MichaelDennis, NatashaJaques, EugeneVinitsky....
Published date-12/01/2020
Tasks:  TransferLearning

Abstract: A wide range of reinforcement learning (RL) problems --- including robustness, transfer learning, unsupervised RL, and emergent complexity --- require specifying a distribution of tasks or environments in which a …

Fair Multiple Decision Making Through Soft Interventions


Authors:  YaoweiHu, YongkaiWu, LuZhang....
Published date-12/01/2020
Tasks:  DecisionMaking, fairness

Abstract: Previous research in fair classification mostly focuses on a single decision model. In reality, there usually exist multiple decision models within a system and all of which may contain a …

Model Class Reliance for Random Forests


Authors:  GavinSmith, RobertoMansilla, JamesGoulding....
Published date-12/01/2020

Abstract: Variable Importance (VI) has traditionally been cast as the process of estimating each variables contribution to a predictive model's overall performance. Analysis of a single model instance, however, guarantees no …

Learning Disentangled Representations and Group Structure of Dynamical Environments


Authors:  RobinQuessard, ThomasBarrett, WilliamClements....
Published date-12/01/2020

Abstract: Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe …

Filter by

Categories

Tags