Transcription of Combining Multiple Sources of Knowledge in ... - …
{{id}} {{{paragraph}}}
Example: barber
Combining Multiple Sources of Knowledge in ... - …
Combining Multiple Sources of Knowledge in Deep CNNs for Action RecognitionEunbyung Park, Xufeng Han, tamara L. Berg, Alexander C. BergUniversity of North Carolina at Chapel deep convolutional neural networks (CNNs)have shown remarkable results for feature learning andprediction tasks, many recent studies have demonstratedimproved performance by incorporating additional hand-crafted features or by fusing predictions from multipleCNNs. Usually, these combinations are implemented viafeature concatenation or by averaging output predictionscores from several CNNs. In this paper, we present newapproaches for Combining different Sources of knowledgein deep learning. First, we propose feature amplification,where we use an auxiliary, hand-crafted, feature ( opti-cal flow) to perform spatially varying soft-gating on inter-mediate CNN feature maps.
Combining Multiple Sources of Knowledge in Deep CNNs for Action Recognition Eunbyung Park, Xufeng Han, Tamara L. Berg, Alexander C. Berg University of North Carolina at Chapel Hill
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: