Chong Cao

Chengwei Shi, Chong Cao, Xin Tong et al.

Head and gaze dynamics are crucial in expressive 3D facial animation for conveying emotion and intention. However, existing methods frequently address facial components in isolation, overlooking the intricate coordination between gaze, head motion, and speech. The scarcity of high-quality gaze-annotated datasets hinders the development of data-driven models capable of capturing realistic, personalized gaze control. To address these challenges, we propose StyGazeTalk, an audio-driven method that generates synchronized gaze and head motion styles. We extract speaker-specific motion traits from gaze-head sequences with a multi-layer LSTM structure incorporating a style encoder, enabling the generation of diverse animation styles. We also introduce a high-precision multimodal dataset comprising eye-tracked gaze, audio, head pose, and 3D facial parameters, providing a valuable resource for training and evaluating head and gaze control models. Experimental results demonstrate that our method generates realistic, temporally coherent, and style-aware head-gaze motions, significantly advancing the state-of-the-art in audio-driven facial animation.

Chong Cao

Porosity has been identified as the key indicator of the durability properties of concrete exposed to aggressive environments. This paper applies ensemble learning to predict porosity of high-performance concrete containing supplementary cementitious materials. The concrete samples utilized in this study are characterized by eight composition features including w/b ratio, binder content, fly ash, GGBS, superplasticizer, coarse/fine aggregate ratio, curing condition and curing days. The assembled database consists of 240 data records, featuring 74 unique concrete mixture designs. The proposed machine learning algorithms are trained on 180 observations (75%) chosen randomly from the data set and then tested on the remaining 60 observations (25%). The numerical experiments suggest that the regression tree ensembles can accurately predict the porosity of concrete from its mixture compositions. Gradient boosting trees generally outperforms random forests in terms of prediction accuracy. For random forests, the out-of-bag error based hyperparameter tuning strategy is found to be much more efficient than k-Fold Cross-Validation.