Submission Data for SC-MPF


Name

SC-MPF


Description

This method is one of the a baselines used for evaluation in TRiPOD paper. In this baseline the human pose dynamics forecasting in preformed in global space with an state-of-the-art method abbreviated to SC-MPF [Socially and contextually aware human motion and pose forecasting, Adeli et. al., RA-L and IROS 2020]. SC-MPF proposes a novel framework to tackle both tasks of human motion (or trajectory) and body skeleton pose forecasting in a unified end-to end pipeline incorporating both scene and social contexts.


Publication title

Socially and Contextually Aware Human Motion and Pose Forecasting


Publication authors

Adeli, V. and Adeli, E. and Reid, I. and Niebles, J.C. and Rezatofighi, H.


Publication venue and year

RA-L & IROS, 2020


Publication URL

https://arxiv.org/abs/2007.06843


Language(s)


Hardware


Website


Source code URL


Creation date

2021-04-16 12:23:56


Metric 80/100 ms 160/240 ms 320/500 ms 400/640 ms 560/900 ms
PoseTrack VAM 78.35852988787578 99.80011883336205 124.3779606540978 138.5226562997446 147.9253240845005
PoseTrack VIM 22.010501558121987 37.990218450530996 64.62139187952212 75.8381305379372 93.53601426763856
3DPW VIM 46.28322500415195 73.88508650733547 130.2369074375134 160.8356617673951 208.445244576733