C.-C. Jay Kuo

TL;DR: A novel 3D Domain Adaptation Network for point cloud data (PointDAN) is proposed, which jointly aligns the global and local features in multi-level and demonstrates the superiority of the model over the state-of-the-art general-purpose DA methods.

TL;DR: In this paper, a data-driven Saak transform with augmented kernels is proposed, which consists of three steps: (1) building the optimal linear subspace approximation with orthonormal bases using the second-order statistics of input vectors, (2) augmenting each transform kernel with its negative, and (3) applying the rectified linear unit (ReLU) to the transform output.

TL;DR: The GEF system outperforms the existing state-of-the-art age estimation methods by a significant margin, and the mean absolute errors of age estimation are reduced from 4.48 to 2.81 years on FG-NET and 3.97 years on MORPH-II.

TL;DR: An on-line audio classification and segmentation system is presented, where audio recordings are classified and segmented into speech, music, several types of environmental sounds and silence based on audio content analysis.

TL;DR: In this article, a learning-based approach is proposed to generate visually coherent completion given a high-resolution image with missing components, which divides the task into inference and translation as two separate steps and models each step with a deep neural network.