Human Dynamics

18 papers with code • 0 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?

Latest papers with no code

Socially and Contextually Aware Human Motion and Pose Forecasting

no code yet • 14 Jul 2020

In this paper, we propose a novel framework to tackle both tasks of human motion (or trajectory) and body skeleton pose forecasting in a unified end-to-end pipeline.

Flow descriptors of human mobility networks

no code yet • 16 Mar 2020

Mobile phone data has enabled the timely and fine-grained study human mobility.

Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision

no code yet • 4 Nov 2019

In contrast to the previous work that aims to solve either the task of pose prediction or trajectory forecasting in isolation, we propose a framework to unify the two problems and address the practically useful task of pedestrian locomotion prediction in the wild.

Forecasting Human Dynamics from Static Images

no code yet • CVPR 2017

This paper presents the first study on forecasting human dynamics from static images.

Going Deeper into Action Recognition: A Survey

no code yet • 16 May 2016

Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation.

Effects of human dynamics on epidemic spreading in C\^{o}te d'Ivoire

no code yet • 30 Apr 2016

However, challenging problems are encountered because of complex epidemic spreading dynamics influenced by spatial structure and human dynamics (including both human mobility and human interaction intensity).

Recurrent Network Models for Human Dynamics

no code yet • ICCV 2015

We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture.

Demodulation of Sparse PPM Signals with Low Samples Using Trained RIP Matrix

no code yet • 1 Sep 2013

Compressed sensing (CS) theory considers the restricted isometry property (RIP) as a sufficient condition for measurement matrix which guarantees the recovery of any sparse signal from its compressed measurements.