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…