Although masks protect us from COVID-19, they cover a substantial portion of the face,eliminates important facial expressions during communications. EmoMask is a human-AI collaborative mask that mediates these interactions in mask-wearing environments through emotion-aware sensorsAI algorithms, which works with humans to create facial expressions. The EmoMask system identifiesdifferentiates expressions using TinyML-based AI algorithm,conducts real-time classificationsregressions to create matching facial expressions during a communication while faces are covered.

We propose a semantic-guided framework (FashionOn+) that generates image-based virtual try-on results with arbitrary poses. FashionOn+ contains three stages: (I) conducts the semantic segmentation to have the prior knowledge of body parts for rendering the corresponding texture in stage (II). (III) refines two salient regions, i.e., faceclothes, to generate high-quality results. With the novel architecture, we win first place in the Multi-pose Virtual Try-on Challenge in CVPR, 2020. Further, we tackle the low-resolution limitation (256x192)achieve high-resolution results (640x480).