Exploring Sub-skeleton Trajectories for Interpretable Recognition of Sign Language
This work addresses sign language recognition, a domain-specific problem for improving communication accessibility, but it appears incremental as it builds on existing trajectory-based methods with geometric features.
The paper tackled the problem of accurately recognizing sign language words to narrow the communication gap between hard and non-hard of hearing people, and their simple methods improved sign recognition over recent state-of-the-art approaches.
Recent advances in tracking sensors and pose estimation software enable smart systems to use trajectories of skeleton joint locations for supervised learning. We study the problem of accurately recognizing sign language words, which is key to narrowing the communication gap between hard and non-hard of hearing people. Our method explores a geometric feature space that we call `sub-skeleton' aspects of movement. We assess similarity of feature space trajectories using natural, speed invariant distance measures, which enables clear and insightful nearest neighbor classification. The simplicity and scalability of our basic method allows for immediate application in different data domains with little to no parameter tuning. We demonstrate the effectiveness of our basic method, and a boosted variation, with experiments on data from different application domains and tracking technologies. Surprisingly, our simple methods improve sign recognition over recent, state-of-the-art approaches.