Searching for fingerspelled content in American Sign Language

TL;DR

This paper introduces FSS-Net, an end-to-end model for searching fingerspelled words in ASL videos, significantly improving retrieval accuracy by jointly detecting fingerspelling and matching it to text.

Contribution

The paper presents the first dedicated model for searching fingerspelled content in sign language videos, addressing a previously unstudied problem.

Findings

FSS-Net outperforms baseline methods on a large ASL fingerspelling dataset.

Joint detection and matching improve search accuracy.

Fingerspelling detection is crucial for sign language video search applications.

Abstract

Natural language processing for sign language video - including tasks like recognition, translation, and search - is crucial for making artificial intelligence technologies accessible to deaf individuals, and is gaining research interest in recent years. In this paper, we address the problem of searching for fingerspelled key-words or key phrases in raw sign language videos. This is an important task since significant content in sign language is often conveyed via fingerspelling, and to our knowledge the task has not been studied before. We propose an end-to-end model for this task, FSS-Net, that jointly detects fingerspelling and matches it to a text sequence. Our experiments, done on a large public dataset of ASL fingerspelling in the wild, show the importance of fingerspelling detection as a component of a search and retrieval model. Our model significantly outperforms baseline methods adapted from prior work on related tasks