Domes to drones: Self-supervised active triangulation for 3d human pose reconstruction supplementary material

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskriftPeer review

5 Citeringar (SciVal)

Sammanfattning

This supplementary provides more insight into our ACTOR model and experimental setup. Section §1 describes the details of the network architecture, implementation, and hyperparameters. §2 elaborates on how we match 2d pose estimates in space and time using instance features. In §3 we provide 2d reprojection errors onto 2d OpenPose [2] estimates on the Panoptic test splits. Finally, §4 describes further dataset details.

Originalspråkengelska
TidskriftAdvances in Neural Information Processing Systems
Volym32
StatusPublished - 2019 jan. 1
Evenemang33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Kanada
Varaktighet: 2019 dec. 82019 dec. 14

Ämnesklassifikation (UKÄ)

  • Matematik

Fingeravtryck

Utforska forskningsämnen för ”Domes to drones: Self-supervised active triangulation for 3d human pose reconstruction supplementary material”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här