Search Results for author:
Found 3 papers, 0 papers with code
CoroNetGAN: Controlled Pruning of GANs via Hypernetworks
Additionally, our approach also outperforms the state-of-the-art methods in achieving better inference time on various smart-phone chipsets and data-types making it a feasible solution for deployment on edge devices.
GRITv2: Efficient and Light-weight Social Relation Recognition
Our research has provided a new state-of-the-art relation recognition model on the PISC relation dataset.
Ranked #1 on
Visual Social Relationship Recognition
on PISC
MOSAIC: Multi-Object Segmented Arbitrary Stylization Using CLIP
Our method can extend to any arbitrary objects, styles and produce high-quality images compared to the current state of art methods.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
