Guangming Shi

TL;DR: This paper proposes the real-time face attendance marking system, which works well in non-cooperative environments, and creates a reference gallery of multimodal facial features, which improves the accuracy and speed of multimmodal face recognition.

TL;DR: Wang et al. as mentioned in this paper proposed dilated mixed convolution module, which mixes dilated convolution and standard convolutions to capture both the fine-grained and long-term dependencies and give weight to neighboring information.

TL;DR: This work proposes a maximum a posteriori estimation-based correspondence retrieval method that uses the significant features as priors to estimate the weak or missing features, and proposes a novel monochromatic maze-like pattern, which is more robust to ambient illumination and the colors in scenes than the traditional patterns.

TL;DR: This paper proposes a joint optimization framework that consists of two main steps: transforming the face model for better alignment and applying face priors for improved depth recovery, and demonstrates that the proposed method can achieve up to 23.8% improvement in depth recovery with more accurate face registrations.

TL;DR: A new distribution prior with enhanced sparsity constraint is considered in the proposed CS framework and exhibits its great superiority than many other spectrum estimation methods especially under the highly-corrupted condition.