79 citations · 174 across the 39 of their papers we have counts for
3 papers · 1 filter
Character Generation through Self-Supervised Vectorization
Gokcen Gokceoglu, Emre Akbas
The prevalent approach in self-supervised image generation is to operate on pixel level representations. While this approach can produce high quality images, it cannot benefit from…
Does depth estimation help object detection?
Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas
Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color. However, estimated depth does not always yield…
Representation Recycling for Streaming Video Analysis
Can Ufuk Ertenli, Ramazan Gokberk Cinbis, Emre Akbas
We present StreamDEQ, a method that aims to infer frame-wise representations on videos with minimal per-frame computation. Conventional deep networks perform feature extraction fro…