David Doermann

Also published under:D. S. Doermann, D. Doermann, David S. Doermann

Affiliation

Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA

Topic

Convolutional Neural Network,Deep Learning,Action Recognition,Convolutional Layers,Feature Learning,Final Prediction,Image Classification,Medical Imaging,Multiple Instance Learning,Neural Network,Object Detection,Otsu’s Method,Prediction Accuracy,Training Images,Training Set,Training Videos,Uncertainty Estimation,Action Classes,Action Instances,Action Localization,Action Proposals,Adaptive Modulation,Advances In Deep Learning,Attention Distillation,Attention Map,Attention Values,Background Scene,Bayesian Inference,Binary Cross-entropy Loss,Binary Label,Binary Selection,Bootstrap Samples,Bounding Box,Central Server,Circle Area,Class Activation Maps,Classification Task,Communication Rounds,Comparable Prediction Accuracy,Competitive Performance,Computer Vision,Confidence Score,Contact Force,Conv Layer,Convolution Operation,Convolutional Neural Networks Backbone,Cost Function,Cost Matrix,Critical Applications,Current Dataset,

Biography

David Doermann received the M.Sc. degree in 1989 and the Ph.D. degree in 1993 from the Department of Computer Science, University of Maryland, College Park.
He is Co-Director of the Laboratory for Language and Media Processing, Institute for Advanced Computer Studies, University of Maryland, and an Adjunct Member of the Graduate Faculty. His research centers widely around the topics of document image analysis and multimedia information processing for digital libraries. He is active in the research community, has organized several symposia with government, industry, and academic participation, has served on numerous boards and program committees, and is an editor of the newly formed International Journal of Document Analysis and Recognition.