M
Massoud Pedram
Researcher at University of Southern California
Publications - 812
Citations - 25236
Massoud Pedram is an academic researcher from University of Southern California. The author has contributed to research in topics: Energy consumption & CMOS. The author has an hindex of 77, co-authored 780 publications receiving 23047 citations. Previous affiliations of Massoud Pedram include University of California, Berkeley & Syracuse University.
Papers
More filters
Journal ArticleDOI
Coarse2Fine: a two-stage training method for fine-grained visual classification
TL;DR: Coarse2Fine as discussed by the authors learns an inverse mapping function from the attended feature maps to the informative regions in the raw image, which will guide the attention maps to better attend the fine-grained features.
Posted Content
Coarse2Fine: A Two-stage Training Method for Fine-grained Visual Classification
TL;DR: This work proposes a training method for visual attention networks, Coarse2Fine, which creates a differentiable path from the input space to the attended feature maps, which will guide the attention maps to better attend the fine-grained features.
Proceedings ArticleDOI
A nested game-based optimization framework for electricity retailers in the smart grid with residential users and PEVs
TL;DR: A novel four-stage nested game model is proposed to model the interaction of the electricity retailer, utility companies, and consumers and demonstrates the effectiveness of the proposed game theoretic modeling and optimization framework.
Journal ArticleDOI
Power-aware bus encoding techniques for i/o and data buses in an embedded system
Wei-Chung Cheng,Massoud Pedram +1 more
TL;DR: A software-only encoding technique is proposed to reduce the power consumption of the processor-memory bus when displaying an image on the LCD using the palette as a coding table for the pixel buffer and reassign the codes according to the image characteristics.
Proceedings ArticleDOI
An efficient semi-analytical current source model for FinFET devices in near/sub-threshold regime considering multiple input switching and stack effect
TL;DR: This paper presents an efficient current source model (CSM) for FinFET devices operating in the near/sub-threshold regime, considering multiple input switching (MIS) and accounting for the effect of internal node voltages of the logic cell.