Accurately determining the clinical positions for each tooth is essential in orthodontics, while most existing solutions heavily rely on inefficient manual design. In this paper, we present the LETA, a dual-branch Latent Encoding based 3D Tooth Alignment. Our system takes as input the segmented individual 3D tooth meshes in the Intra-oral Scanner (IOS) dental surfaces, and automatically predicts the proper 3D pose transformation for each tooth. LETA includes three components: an Encoder that learns a latent code of dental pointcloud, a Projector that transforms the latent code of misaligned teeth to predicted aligned ones, and a Solver to estimate the transformation between different dental latent codes. A key novelty of LETA is that we extract the features from the ground truth (GT) aligned teeth to guide network learning during training. To effectively learn tooth features, our Encoder employs an improved point-wise convolutional operation and an attention-based network to extract local shape features and global context features respectively. Extensive experimental results on a large-scale dataset with 9,868 IOS surfaces demonstrate that LETA can achieve state-of-the-art performance. A further clinical applicability study reveals that our method can reduce orthodontists' workload over 60% compared to starting tooth alignment from scratch, demonstrating the strong potential of deep learning for future digital dentistry.

In this paper, we study the secrecy precoding problem for simultaneous wireless information and power transfer (SWIPT) in a multiple-input multiple-output (MIMO) relay network. The problem is formulated as a noncooperative game, where the network utility, defined as the nonnegative sum of the achievable secrecy rate and the harvested energy, is regarded as the common payoff, and the source and the relay are assumed as two rational game players. The formulated game is proven to be a potential game, which always processes at least one pure-strategy Nash equilibrium (NE), and the optimal transmit strategy profile that maximizes the network utility also constitutes a pure-strategy NE of it. Since the best-response problems of the proposed game constitute difference convex (DC)-type programming problems, we solve them by employing a successive convex approximation (SCA) method. With the SCA method, the two best-response problems can be iteratively solved through successive convex programming of their convexified versions. Then, based on the best-response dynamic, a distributed precoding algorithm is developed to obtain a feasible NE solution the proposed game. Numerical simulations are further provided to demonstrate it. Results show that our algorithm can converge fast to a near-optimal solution with guaranteed convergence.

Tabletop hand tracking techniques have evolved much during the last few years from single to multiple cameras, offering users an improved interactive experience. MirrorTrack is one of such techniques. This paper demonstrates the comparison of accuracy between MirrorTrack and top-down approach, which is generally used for table top tasks. In this paper, we focus on the comparison of distance errors in finger trajectory, and clicking errors by manual monitoring.

Detection of meeting events is one of the most important tasks in multimodal analysis of planning meetings. Speaker detection is a key step for extraction of most meaningful meeting events. In this paper, we present an approach of speaker localization using combination of visual and audio information in multimodal meeting analysis. When talking, people make a speech accompanying mouth movements and hand gestures. By computing correlation of audio signals, mouth movements, and hand motion, we detect a talking person both spatially and temporally. Three kinds of features are extracted for speaker localization. Hand movements are expressed by hand motion efforts; audio features are expressed by computing 12 mel-frequency cepstral coefficients from audio signals, and mouth movements are expressed by normalized cross-correlation coefficients of mouth area between two successive frames. A time delay neural network is trained to learn the correlation relationships, which is then applied to perform speaker localization. Experiments and applications in planning meeting environments are provided.

We present an adaptive skin color model for hand gesture tracking which is applied to cross-modal analysis of planning meetings. We build a skin color model with the Gaussian distribution and a skin color filter for each participant in meetings. By combining with the vector coherence mapping (VCM) algorithm, we track hand motion and obtain 3D trajectories. The hand gesture stream is extracted from hand motion trajectories. Different skin color models are created for different people to handle the differences of skin color. We update each model dynamically to adapt changes of environments. A parallel system has been implemented to track and extract hand motion trajectories. Examples of hand motion gesture tracking in meeting environments are provided. The applications of the adaptive skin color model can increase the speed of hand tracking