Humans have used sketching to depict our visual world since prehistoric times. Even today,
sketching is possibly the only rendering technique readily available to all humans. This …

In this paper we present the first large-scale scene attribute database. First, we perform
crowd-sourced human studies to find a taxonomy of 102 discriminative attributes. Next, we …

Describing clothing appearance with semantic attributes is an appealing technique for many
important applications. In this paper, we propose a fully automated system that is capable of …

In this paper we propose an approach to holistic scene understanding that reasons jointly
about regions, location, class and spatial extent of objects, presence of a class in the image …

We introduce the problem of scene viewpoint recognition, the goal of which is to classify the
type of place shown in a photo, and also recognize the observer's viewpoint within that …

We present a holistic data-driven approach to image description generation, exploiting the
vast amount of (noisy) parallel image data and associated natural language descriptions …

Empirically, we find that, despite the class-specific features owned by the objects appearing
in the images, the objects from different categories usually share some common patterns …

In many visual classification tasks the spatial distribution of discriminative information is (i)
non uniform eg personreading'can be distinguished fromtaking a photo'based on the area …

As visual recognition scales up to ever larger numbers of categories, maintaining high
accuracy is increasingly difficult. In this work, we study the problem of optimizing accuracy …

In this paper, we present a highly data-driven approach to the task of single image super-
resolution. Super-resolution is a challenging problem due to its massively under-constrained …