Memorization of training data is an active research area, yet our
unders...
Text-to-image diffusion models have demonstrated an unparalleled ability...
Reconstructing samples from the training set of trained neural networks ...
Large vision-language models (VLMs), such as CLIP, learn rich joint
imag...
Diffusion models exhibited tremendous progress in image and video genera...
Text-conditioned image editing has recently attracted considerable inter...
Videos obtained by rolling-shutter (RS) cameras result in spatially-dist...
Understanding to what extent neural networks memorize training data is a...
Reconstructing natural videos from fMRI brain recordings is very challen...
GANs are able to perform generation and manipulation tasks, trained on a...
Despite remarkable progress on visual recognition tasks, deep neural-net...
Most advanced video generation and manipulation methods train on a large...
In the past few years, significant advancements were made in reconstruct...
Image classification models can depend on multiple different semantic
at...
Single image generative models perform synthesis and manipulation tasks ...
A basic operation in Convolutional Neural Networks (CNNs) is spatial res...
We wish to automatically predict the "speediness" of moving objects in
v...
When a very fast dynamic event is recorded with a low-framerate camera, ...
We present a novel GAN-based model that utilizes the space of deep featu...
Super resolution (SR) methods typically assume that the low-resolution (...
Reconstructing observed images from fMRI brain recordings is challenging...
We propose an approach to distinguish between correct and incorrect imag...
Many seemingly unrelated computer vision tasks can be viewed as a specia...
Good Visual Retargeting changes the global size and aspect ratio of a na...
Deep Learning has led to a dramatic leap in Super-Resolution (SR) perfor...
The ability to detect similar actions across videos can be very useful f...