Existing image editing tools, while powerful, typically disregard the
un...
We present VISPROG, a neuro-symbolic approach to solving complex and
com...
Computer vision models excel at making predictions when the test distrib...
General purpose vision (GPV) systems are models that are designed to sol...
We propose a new framework for understanding and representing related sa...
A special purpose learning system assumes knowledge of admissible tasks ...
A learning curve models a classifier's test error as a function of the n...
Phrase grounding, the problem of associating image regions to caption wo...
We propose to learn word embeddings from visual co-occurrences. Two word...
We show that with an appropriate factorization, and encodings of layout ...
Imagining a scene described in natural language with realistic layout an...
An important goal of computer vision is to build systems that learn visu...
We propose an approach for 3D reconstruction and segmentation of a singl...