Yong Zhao

Object grasping is a crucial technology enabling robots to perceive and interact with the environment sufficiently. However, in practical applications, researchers are faced with missing or noisy ground truth while training the convolutional neural network, which decreases the accuracy of the model. Therefore, different loss functions are proposed to deal with these problems to improve the accuracy of the neural network. For missing ground truth, a new predicted category probability method is defined for unlabeled samples, which works effectively in conjunction with the pseudo-labeling method. Furthermore, for noisy ground truth, a symmetric loss function is introduced to resist the corruption of label noises. The proposed loss functions are powerful, robust, and easy to use. Experimental results based on the typical grasping neural network show that our method can improve performance by 2 to 13 percent.

Smile recognition is a very important topic in image processing and deep learning, and has a certain practical significance. At present, existing datasets tend to have simple backgrounds or imbalanced ethnicities. And researchers need to build convolutional neural networks empirically. To address these problems, we first construct a comprehensive dataset which contains 10,392 images of four major races (i.e., White, Asian, American Native or Pacific Islander, and Black or African American) in complex backgrounds. Our dataset exhibits larger variations in background, illumination, and ethnicity. And then, we apply Bayesian neural architecture search algorithm to automatically build the optimal convolutional network architecture and perform model training. The network architecture can be repeatedly searched and optimized through Bayesian optimizer in the specified time. Through the comparisons of experimental data, the performance of our network is better than those of the classical networks.

This paper introduces a simple but powerful segmentation algorithm for 3D meshes. Our algorithm consists of two stages: over-segmentation and region fusion. In the first stage, adaptive space partition is applied to perform over-segmentation, which is very efficient. In the second stage, we define a new intra-region difference, inter-region difference, and fusion condition with the help of various shape features and propose an iterative region fusion method. As the region fusion process is feature aware, our algorithm can deal with complex 3D meshes robustly. Massive qualitative and quantitative experiments also validate the advantages of the proposed algorithm.

Segmenting 3D mesh is a difficult topic in computer graphics. This paper proposes a new mesh segmentation algorithm. First, we over-segment the input mesh to generate a series of superfacets. Second, we introduce a novel region fusion algorithm to obtain the segmentation result. Various experiments show that our algorithm is able to handle 3D meshes with complex shape and rich details. Even though the input mesh has noises or holes our algorithm can still achieve satisfactory results.