Guobin Tu

Sign Language Translation (SLT) is a challenging cross-modal task requiring joint modeling of manual articulations and non-manual signals. Existing gloss-free SLT methods effectively capture gestural dynamics but often underutilize facial expressions, which play crucial grammatical and disambiguating roles. This limitation can cause semantic degradation when distinct concepts share similar manual configurations. To address this issue, we propose FEA-SLT (Facial-Expression-Aware Sign Language Translation), a gloss-free end-to-end framework that uses facial dynamics as semantic anchors for resolving manual ambiguity. FEA-SLT employs a domain-transferred facial encoder to extract expression-sensitive representations and integrates them with manual features through a linguistically constrained Facial-Expression-Aware Fusion (FEAF) module. FEAF captures reciprocal dependencies between manual and facial channels via bidirectional modulation, enhancing syntactic fidelity. Experiments on PHOENIX14T and CSL-Daily show that FEA-SLT achieves state-of-the-art BLEU performance among gloss-free methods, while targeted analyses confirm improved translation of facial-sensitive utterances.

Finding time series patterns is an important problem in finance, healthcare, climatology, and manufacturing, where temporal data analysis informs critical decision-making processes. Existing approaches use examples, sketches, and natural language (NL) for time series pattern querying, but precisely formulating complex queries, inspecting query interpretations, and refining queries iteratively remain challenging. Nevertheless, NL is a promising modality for pattern specification, balancing expressiveness and preciseness while providing an intuitive means of articulating query intent. This paper introduces ChronoMantic, an NL-driven interactive interface for time series pattern querying. The tool provides glyph-based feedback on query interpretation and supports iterative querying through by-example refinement. We illustrate ChronoMantic’s workflow through two usage scenarios, assess its retrieval performance on a manually annotated benchmark, and evaluate its query effectiveness and usability via a two-stage user study.