We propose a new paradigm to automatically generate training data with
a...
Current text-to-image generation models often struggle to follow textual...
Training computer vision models usually requires collecting and labeling...
Weakly supervised object detection (WSOD) enables object detectors to be...
Visual attention helps achieve robust perception under noise, corruption...
Contrastive learning relies on an assumption that positive pairs contain...
It was recently shown that the structure of convolutional neural network...
Biodiversity conservation depends on accurate, up-to-date information ab...
Camera equipped drones are nowadays being used to explore large scenes a...
Cinemagraphs are a compelling way to convey dynamic aspects of a scene. ...
The significant optical and size benefits of using a curved focal surfac...
We present a system for converting a fully panoramic (360^∘) video into
...
Custom optics is a necessity for many imaging applications. Unfortunatel...