April 24, 2017

Taxonomy augmented object recognition

Realistic scene object recognition in computer vision still faces great challenges due to the large intra-class variation of object images caused by factors like object appearance variation and viewpoint change. To address this challenge, we propose to exploit the semantic relationships embedded in object taxonomy for improved object recognition. Specifically, we exploit the relationships in the object taxonomy to augment the learning of object classifiers. We utilize two types of relationships in the taxonomy, including the overall relationship and the local relationship. Our proposed approach jointly incorporates both the overall relationship as the loss function for classifier learning, and the local relationship as classifier learning constraints. Experiments on benchmark datasets demonstrate the effectiveness of our method in incorporating taxonomy for object recognition compared to the state-art-the-art methods.

View Original Article

Recent Publications

May 22, 2017

Multidimensional Resource Allocation in NFV Cloud

  • Goldstein M.
  • Raz D.
  • Segall I.

Network Function Virtualization (NFV) is a new networking paradigm in which network functionality is implemented on top of virtual infrastructure deployed over COTS servers. One of the main motivations for the shift of telco operators into this paradigm is cost reduction, thus the efficient use of resources is an important ...

May 20, 2017

The Actual Cost of Software Switching for NFV Chaining

  • Caggiani Luizelli M.
  • Raz D.
  • Saar Y.
  • Yallouz J.

Network Function Virtualization (NFV) is a novel paradigm allowing flexible and scalable implementation of network services on cloud infrastructure. An important enabler for the NFV paradigm is software switching, which needs to satisfy rigid network requirements such as high throughput and low latency. Despite recent research activities in the field ...

May 08, 2017

Coexistence-aware dynamic channel allocation for 3.5 GHz shared spectrum systems

The paradigm of shared spectrum allows secondary devices to opportunistically access spectrum bands underutilized by primary owners. As the first step, the FCC targeted sharing the 3.5 GHz (3550–3700 MHz) federal spectrum with commercial systems. The proposed rules require a Spectrum Access System to implement a three-tiered spectrum management framework, ...