activity
20212025
most citedLeveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes

2 citations · 7 across the 17 of their papers we have counts for

collaborators
Showing 2021Show all

1 paper · 1 filter

cs.CV2021

Extended Self-Critical Pipeline for Transforming Videos to Text (TRECVID-VTT Task 2021) -- Team: MMCUniAugsburg

Philipp Harzig, Moritz Einfalt, Katja Ludwig +1

The Multimedia and Computer Vision Lab of the University of Augsburg participated in the VTT task only. We use the VATEX and TRECVID-VTT datasets for training our VTT models. We ba…