Congratulations to Crowd Lab Ph.D. student Vikram Mohanty and computer science major David Thames for winning the inaugural Best Poster/Demo Award at HCOMP 2018 in Zurich, Switzerland. Their poster/demo was titled, “Are 1,000 Features Worth A Picture? Combining Crowdsourcing and Face Recognition to Identify Civil War Soldiers.”
Author: Kurt Luther
Dr. Kurt Luther is an associate professor of computer science and (by courtesy) history at Virginia Tech, where he directs the Crowd Intelligence Lab.
Beta release of Photo Sleuth software in Gettysburg
The Civil War Photo Sleuth team released a beta version of our software for identifying unknown Civil War photos at the 45th Civil War Artifact and Collectibles Show in Gettysburg, PA. Our table was set up next to our partners at Military Images Magazine. The team was excited to help dozens of attendees sign up for the site, and these new users tentatively identified several unknown soldier photos during the show.
We also demoed an earlier version of the Photo Sleuth software at the previous year’s Gettysburg show in 2017. More details here.
Poster presented at HCIC 2018
Crowd Lab Ph.D. student Sukrit Venkatagiri and postdoc Jacob Thebault-Spieker presented a poster on their research using crowdsourcing to analyze satellite imagery for geolocation purposes at the Human-Computer Interaction Consortium (HCIC 2018) conference in Watsonville, CA. The poster, seen below, was titled, “Verifying Truth from the Ground: Leveraging Human Strengths in the Image Geolocation Process“.
Welcome, Summer 2018 interns!
We are excited to welcome three undergraduate interns to the Crowd Lab’s Arlington location this summer. Their research is funded by the Research Experience for Undergraduates (REU) program of the National Science Foundation.
Aliza Camacho is a Computer Science and Anthropology double-major at Wellesley College. She will be working on the GroundTruth project.
Ryan Russell is a Computer and Information Sciences major at Virginia Military Institute. He will be working on the Photo Sleuth project.
Natalie Robinson is a History and Public Relations double-major at the University of Georgia. She will be working on the Photo Sleuth project.
Won Grand Prize in Microsoft Cloud AI Research Challenge
Congratulations to Crowd Lab Ph.D. student Vikram Mohanty and computer science major David Thames for winning the Grand Prize in the Microsoft Cloud AI Research Challenge. Their submission was titled, “Civil War Photo Sleuth” and the prize was $25,000.
The American Soldier in World War II launched on Zooniverse
On May 8, the anniversary of Victory in Europe (V-E) Day, we launched The American Soldier in World War II, a crowdsourced transcription project featured on the Zooniverse platform. This project is the result of a year-long collaboration between Virginia Tech’s History and Computer Science departments, University Libraries, the National Archives, and Zooniverse, with funding by the NEH. VT History professor Ed Gitre is the PI. Dr. Luther is Co-PI and technical lead of the project, and Crowd Lab Ph.D. candidate Nai-Ching Wang is the lead developer.
Our launch included a transcribe-a-thon event at multiple physical and online locations and was based in the Athenaeum digital humanities center at VT. In its first 24 hours, the project attracted over 5,000 contributions. More photos of the event are available on VT Department of Computer Science’s Facebook page.
Thanks to our many collaborators and transcribers for making the event a success!
Please check out some of the publicity for the project to learn more:
- Virginia Tech press release: Victory in Europe Day to be commemorated with national effort to make available insights of American soldiers during World War II
- Stars and Stripes: WWII in a new light: Anonymous soldier surveys tell stories of morale, race relations
- WVTF (local NPR affiliate): What They Were Thinking: WWII Soldiers’ Insights to Become Public Data Base
- Social Science Research Council: Understanding the American Soldier: The SSRC and Social Science in World War II
Received COE Outstanding New Assistant Professor Award
Dr. Luther received the 2018 Dean’s Award for Outstanding New Assistant Professor Award in the College of Engineering.
Paper accepted for IJCAI 2018
Our paper on geolocating images using crowdsourcing and diagramming was accepted for the International Joint Conference on Artificial Intelligence (IJCAI 2018) in Stockholm, Sweden. Dr. Luther will give the presentation. Congratulations to co-authors and Crowd Lab alumni Rachel Kohler and John Purviance!
Placed 3rd at 2018 VTURCS symposium
Congratulations to Crowd Lab undergraduate researcher Anne Hoang for winning 3rd place in the Faculty Choice category at the 2018 Virginia Tech Undergraduate Research in Computer Science (VTURCS) Symposium. There were 37 submissions including 22 capstone projects and 15 research projects.
Anne also won 1st place in the Capstone category and 1st place in the Marston Awards (industry pick) category. Amazing!
The Crowd Lab regularly participates in the VTURCS Symposium. Last year, our teams placed 1st and 3rd in the Faculty Choice category.
Presentation accepted for Collective Intelligence 2018
Our preliminary work on the Civil War Photo Sleuth project, which combines crowdsourcing and face recognition technology to identify unknown American Civil War soldier photos, was accepted to ACM Collective Intelligence 2018 in the most competitive oral presentation category (32% acceptance rate). We’ll be traveling to Zurich, Switzerland to present this work. The extended abstract is available online.
Congratulations to co-authors Crowd Lab Ph.D. student Vikram Mohanty and computer science undergraduate David Thames.