Higher dimensional data such as video and 3D are the leading edge of multimedia retrieval
and computer vision research. In this survey, we give a comprehensive overview and key …

When the two eyes view discrepant monocular stimuli, stable single vision gives way to
alternating periods of monocular dominance; this is the well-known but little understood …

Convolutional neural networks (CNNs) are inherently limited to model geometric
transformations due to the fixed geometric structures in its building modules. In this work, we …

In this paper, we propose a novel benchmark for evaluating local image descriptors. We
demonstrate that the existing datasets and evaluation protocols do not specify …

It is well known that contextual and multi-scale representations are important for accurate
visual recognition. In this paper we present the Inside-Outside Net (ION), an object detector …

Convolutional networks are powerful visual models that yield hierarchies of features. We
show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels …

Recognition algorithms based on convolutional networks (CNNs) typically use the output of
the last layer as feature representation. However, the information in this layer may be too …

In this work we propose a technique that transfers supervision between images from
different modalities. We use learned representations from a large labeled modality as …

Multi-resolution image features may be approximated via extrapolation from nearby scales,
rather than being computed explicitly. This fundamental insight allows us to design object …

In this paper, we compare the performance of descriptors computed for local interest
regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid …