| Presentation # | 10 |
| Session: | Detection, Paralinguistics and Coding |
| Session Time: | Wednesday, December 19, 13:30 - 15:30 |
| Presentation Time: | Wednesday, December 19, 13:30 - 15:30 |
| Presentation: |
Poster
|
| Topic: |
Multimodal processing: |
| Paper Title: |
AMERICAN SIGN LANGUAGE FINGERSPELLING RECOGNITION IN THE WILD |
| Authors: |
Bowen Shi; Toyota Technological Institute at Chicago | | |
| | Aurora Martinez Del Rio; University of Chicago | | |
| | Jonathan Keane; University of Chicago | | |
| | Jonathan Michaux; Toyota Technological Institute at Chicago | | |
| | Diane Brentari; University of Chicago | | |
| | Greg Shakhnarovich; Toyota Technological Institute at Chicago | | |
| | Karen Livescu; Toyota Technological Institute at Chicago | | |
| Abstract: |
We address the problem of American Sign Language fingerspelling recognition ``in the wild'', using videos collected from websites. We introduce the largest data set available so far for the problem of fingerspelling recognition, and the first using naturally occurring video data. Using this data set, we present the first attempt to recognize fingerspelling sequences in this challenging setting. Unlike prior work, our video data is extremely challenging due to low frame rates and visual variability. To tackle the visual challenges, we train a special-purpose signing hand detector using a small subset of our data. Given the hand detector output, a sequence model decodes the hypothesized fingerspelled letter sequence. For the sequence model, we explore attention-based recurrent encoder-decoders and connectionist temporal classification-based approaches. As the first attempt at fingerspelling recognition in the wild, this work is intended to serve as a baseline for future work on sign language recognition in realistic conditions. We find that, as expected, letter error rates are much higher than in previous work on more controlled data, and we analyze the sources of error and effects of model variants. |