• Citations Per Year
Learn More
Spatial relationships between objects provide important information for text-based image retrieval. As users are more likely to describe a scene from a real world perspective, using 3D spatial relationships rather than 2D relationships that assume a particular viewing direction, one of the main challenges is to infer the 3D structure that bridges images(More)
In this paper, we study the problem of multiuser (MU) scheduling in a MU-MIMO system with imperfect channel state information (CSI) feedback. The CSI feedback for scheduling is considered as a channel direction quantization with feedback delay effect. Inspired by the conventional zero-forcing (ZF) based user scheduling, we present an improved user selection(More)
Understanding the visual relationship between two objects involves identifying the subject, the object, and a predicate relating them. We leverage the strong correlations between the predicate and the 〈subj, obj〉 pair (both semantically and spatially) to predict predicates conditioned on the subjects and the objects. Modeling the three entities jointly more(More)
  • 1