arxiv:2204.04812
Mariya Vasileva
mvasil
AI & ML interests
Generative models, diffusion, controllable generation, text-to-video, text-to-image, audio-to-video, neural VFX, graph theory
Recent Activity
updated
a dataset
about 21 hours ago
mvasil/polyvore-outfits
authored
a paper
about 24 hours ago
Why do These Match? Explaining the Behavior of Image Similarity Models
authored
a paper
about 24 hours ago
OutfitTransformer: Learning Outfit Representations for Fashion
Recommendation
Organizations
