Germany

S. Ging

Advanced
@simon-ging

Doctoral Researcher in Vision-Language Learning. Experience in Image-Text Retrieval, Video Captioning, LLMs

lmb.informatik.uni-freiburg.de/people/gings/

coot-videotext. COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

291

fasttext-numpy2. Library for fast text representation and classification. Fix compatibility with numpy 2

15

typedparser. Extension for python argparse with typehints and typechecks.

4

rl-continuouscartpole. University Project, Reinforcement Learning with DQN on a modified cartpole scenario.

2

packg. Collection of utilities used in other python projects.

1

dotfiles. Configs and installers for bash and other software

1

visiontext. Utilities for deep learning on multimodal data.

1
7
Apply