We present COMEDIAN, a novel pipeline to initialize spatio-temporal
tran...
End-to-end reinforcement learning on images showed significant progress ...
Contrastive representation learning has proven to be an effective
self-s...
We present a new self-supervised pre-training of Vision Transformers for...
In video surveillance applications, person search is a challenging task
...
Contrastive representation learning has proven to be an effective
self-s...
In recent years, we have witnessed increasingly high performance in the ...
In this paper, we present a novel approach, called Deep MANTA (Deep
Many...