Inside the Computer Society
Upcoming Conferences
We solicit high-quality original research papers (and significant work-in-progress papers) in any aspect of Big Data with emphasis on 5Vs (Volume, Velocity, Variety, Value and Veracity), including the Big Data challenges in scientific and engineering, social, sensor/IoT/IoE, and multimedia (audio, v...
Los Angeles, USA
09-12
Dec
The International Symposium on High‐ Performance Computer Architecture provides a high‐quality forum for scientists and engineers to present their latest research findings in this rapidly‐changing field. Authors are invited to submit papers on all aspects of high‐performance computer archite...
San Diego, USA
22-26
Feb
Recent efforts in computer vision have demonstrated impressive successes on a variety of real-world challenges. WACV conferences provide a forum for computer vision researchers working on practical applications to share their latest developments. WACV 2020 solicits high-quality, original submissions...
Snowmass Village, USA
02-05
Mar
Trending from the Computer Society Digital Library
IEEE Security & Privacy
Gertjan Franken
Computer Science, KU Leuven, Belgium
Online abuses give browser users an incentive to employ third-party cookie policies. These policies, built directly into the browser or provided through extensions, are intended to enhance the user's security and privacy. Unfortunately, virtually every policy can be bypassed.
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Kaiming He
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of l...
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bo Yang
Department of Computer Science, University of Oxford, Oxford, United Kingdom
In this paper, we propose a novel approach, 3D-RecGAN++, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike existing work which typically requires multiple views of the same object or class labels to recover...