Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- University Libraries (2)
- Academic library (1)
- Ad-Corre loss (1)
- Convolutional neural network (1)
- Daniel Felix Ritchie School of Engineering and Computer Science (1)
-
- Digital collections (1)
- Digital libraries (1)
- Elastic search (1)
- Electrical and Computer Engineering (1)
- Facial emotion recognition (1)
- Facial expression recognition (1)
- Indexing (1)
- Information technology (1)
- Integration architecture (1)
- Libraries (1)
- Loss function (1)
- Management models (1)
- Open-source software (1)
- Project planning (1)
- Search (1)
- Search engine (1)
- Service management (1)
- Third space (1)
- Vertical cooperation (1)
- Women (1)
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
Ad-Corre: Adaptive Correlation-Based Loss For Facial Expression Recognition In The Wild, Ali Pourramezan Fard, Mohammad H. Mahoor
Ad-Corre: Adaptive Correlation-Based Loss For Facial Expression Recognition In The Wild, Ali Pourramezan Fard, Mohammad H. Mahoor
Electrical and Computer Engineering: Faculty Scholarship
Automated Facial Expression Recognition (FER) in the wild using deep neural networks is still challenging due to intra-class variations and inter-class similarities in facial images. Deep Metric Learning (DML) is among the widely used methods to deal with these issues by improving the discriminative power of the learned embedded features. This paper proposes an Adaptive Correlation (Ad-Corre) Loss to guide the network towards generating embedded feature vectors with high correlation for within-class samples and less correlation for between-class samples. Ad-Corre consists of 3 components called Feature Discriminator, Mean Discriminator, and Embedding Discriminator. We design the Feature Discriminator component to guide …
Building A Library Search Infrastructure With Elasticsearch, Kim Pham, Fernando Reyes, Jeff Rynhart
Building A Library Search Infrastructure With Elasticsearch, Kim Pham, Fernando Reyes, Jeff Rynhart
University Libraries: Faculty Scholarship
This article discusses our implementation of an Elastic cluster to address our search, search administration and indexing needs, how it integrates in our technology infrastructure, and finally takes a close look at the way that we built a reusable, dynamic search engine that powers our digital repository search. We cover the lessons learned with our early implementations and how to address them to lay the groundwork for a scalable, networked search environment that can also be applied to alternative search engines such as Solr.
A Vertical Cooperation Model To Manage Digital Collections And Institutional Resources, Jack M. Maness, Kim Pham, Fernando Reyes, Jeff Rynhart
A Vertical Cooperation Model To Manage Digital Collections And Institutional Resources, Jack M. Maness, Kim Pham, Fernando Reyes, Jeff Rynhart
University Libraries: Faculty Scholarship
The technology space of the University of Denver Libraries to manage digital collections and institutional resources isn’t relegated to one department on campus – rather, it distributed across a network of collaborators with the skills and expertise to provide that support. The infrastructure, which is comprised of an archival metadata management system (Archivespace), a digital repository (Node.js + ElasticSearch), preservation storage (ArchivesDirect), and a streaming server (Kaltura) is independently but cooperatively managed across IT, library departments and vendors. The coordinated eort of digital curation activities still allows each group to focus on the service they have the most vested interest …
Essentialism, Social Construction, Or Individual Differences, Jenelys Cox, Jeff Rynhart, Shea-Tinn Yeh
Essentialism, Social Construction, Or Individual Differences, Jenelys Cox, Jeff Rynhart, Shea-Tinn Yeh
University Libraries: Staff Scholarship
Per the United States Department of Labor Women’s Bureau’s latest available statistics, the percentage of women employed in computer and information technology occupations was consistently lower than the average for all occupations. When broken down by selected characteristics, these numbers range from 12.4% in computer network architectures to 35.2% in web development. Is this trend reflected in the libraries? Although no comprehensive statistics are available for women in library IT, Lamont’s study does reflect the same trend in that the number of women as library IT department heads has been about one half that of men between 2004-2008. Why is …