Deconvolution-and-convolution Networks

no code implementations • 22 Mar 2021 • Yimin Yang, Wandong Zhang, Jonathan Wu, Will Zhao, Ao Chen

2D Convolutional neural network (CNN) has arguably become the de facto standard for computer vision tasks.

L2-Constrained RemNet for Camera Model Identification and Image Manipulation Detection

no code implementations • 10 Sep 2020 • Abdul Muntakim Rafi, Jonathan Wu, Md. Kamrul Hasan

Furthermore, we attain an overall accuracy of 99. 68% in image manipulation detection, which implies that it can be used as a general-purpose network for image forensic tasks.

General Classification Image Forensics +2

Deep Networks with Fast Retraining

no code implementations • 13 Aug 2020 • Wandong Zhang, Yimin Yang, Jonathan Wu

Compared to other learning strategies, the proposed learning pipeline has robustness against the hyper-parameters, and the requirement of computational resources is significantly reduced.

Image Classification

Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions

no code implementations • 12 Oct 2016 • Jiawei Chen, Jonathan Wu, Janusz Konrad, Prakash Ishwar

Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos.

Action Recognition Temporal Action Localization