MyoSem: Aligning Electromyography to Natural-Language Action Semantics for Hand Action Understanding
Researchers have developed MyoSem, a new framework designed to align electromyography (EMG) signals with natural language descriptions of hand actions. This approach moves beyond traditional classification by enabling bidirectional retrieval between EMG data and text, allowing for queries based on action descriptions. MyoSem has demonstrated strong performance in EMG-to-text retrieval and shows good generalization across different users and scenarios, offering a novel paradigm for language-mediated EMG action understanding. AI