PopSign ASL v1.0: An Isolated American Sign Language Dataset Collected via Smartphones

Abstract

Searching for the meaning of an unfamiliar sign-language word in a dictionary is difficult for learners, but emerging sign-recognition technology will soon enable users to search by submitting a video of themselves performing the word they recall. However, sign-recognition technology is imperfect, and users may need to search through a long list of possible results when seeking a desired result. To speed this search, we present a hybrid-search approach, in which users begin with a video-based query and then filter the search results by linguistic properties, e.g., handshape. We interviewed 32 ASL learners about their preferences for the content and appearance of the search-results page and filtering criteria. A between-subjects experiment with 20 ASL learners revealed that our hybrid search system outperformed a video-based search system along multiple satisfaction and performance metrics. Our findings provide guidance for designers of video-based sign-language dictionary search systems, with implications for other search scenarios.

Publication
In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track
Thad E. Starner
Thad E. Starner
Professor at Georgia Institute of Technology
Sean Forbes
Sean Forbes
CEO DPAN
Matthew So
Matthew So
Student at Georgia Institute of Technology
David Martin
David Martin
Student at Georgia Institute of Technology
Rohit Sridhar
Rohit Sridhar
Student at Georgia Institute of Technology
Gururaj Deshpande
Gururaj Deshpande
Student at Georgia Institute of Technology
Sam S. Sepah
Sam S. Sepah
Program Manager at Google
Sahir Shahryar
Sahir Shahryar
Former Student at Georgia Institute of Technology
Khushi Bhardwaj
Khushi Bhardwaj
Student at Georgia Institute of Technology
Tyler Kwok
Tyler Kwok
Student at Georgia Institute of Technology
Daksh Sehgal
Daksh Sehgal
Student at Georgia Institute of Technology
Saad Hassan
Saad Hassan
Assistant Professor

My research interests include human-computer interaction (HCI), accessibility, and computational social science.

Bill Neubauer
Bill Neubauer
Student at Georgia Institute of Technology
Sofia A. Vempala
Sofia A. Vempala
Student at Georgia Institute of Technology
Alec Tan
Alec Tan
Student at Georgia Institute of Technology
Jocelyn Heath
Jocelyn Heath
Student at Georgia Institute of Technology
Unnathi U. Kumar
Unnathi U. Kumar
Student at Georgia Institute of Technology
Priyanka V. Mosur
Priyanka V. Mosur
Student at Georgia Institute of Technology
Rajandeep Singh
Rajandeep Singh
Student at Georgia Institute of Technology
Christopher Z. Cui
Christopher Z. Cui
Student at Georgia Institute of Technology
Glenn Cameron
Glenn Cameron
Product Marketing Manager at Google
Sohier Dane
Sohier Dane
Senior Developer Relations Engineer at Google
Garrett Tanzer
Garrett Tanzer
Software Engineer at Google