Digital orthodontics represents a prominent and critical application of computer vision technology in the medical field. So far, the labor-intensive process of collecting clinical data, particularly in acquiring paired 3D orthodontic teeth models, constitutes a crucial bottleneck for developing tooth arrangement neural networks. Although numerous general 3D shape generation methods have been proposed, most of them focus on single-object generation and are insufficient for generating anatomically structured teeth models, each comprising 24-32 segmented teeth. In this paper, we propose TeethGenerator, a novel two-stage framework designed to synthesize paired 3D teeth models pre- and post-orthodontic, aiming to facilitate the training of downstream tooth arrangement networks. Specifically, our approach consists of two key modules: (1) a teeth shape generation module that leverages a diffusion model to learn the distribution of morphological characteristics of teeth, enabling the generation of diverse post-orthodontic teeth models; and (2) a teeth style generation module that synthesizes corresponding pre-orthodontic teeth models by incorporating desired styles as conditional inputs. Extensive qualitative and quantitative experiments demonstrate that our synthetic dataset aligns closely with the distribution of real orthodontic data, and promotes tooth alignment performance significantly when combined with real data for training. The code and dataset are available at https://github.com/lcshhh/teeth_generator.

Teeth localization, segmentation, and labeling in 2D images have great potential in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, general instance segmentation frameworks are incompetent due to 1) the sub-tle differences between some teeth’ shapes (e.g., maxillary first premolar and second premolar), 2) the teeth's position and shape variation across subjects, and 3) the presence of abnormalities in the dentition (e.g., caries and edentulism). To address these problems, we propose a ViT-based frame-work named TeethSEG, which consists of stacked Multi-Scale Aggregation (MSA) blocks and an Anthropic Prior Knowledge (APK) layer. Specifically, to compose the two modules, we design a unique permutation-based upscaler to ensure high efficiency while establishing clear segmentation boundaries with multi-head selflcross-gating layers to emphasize particular semantics meanwhile maintaining the divergence between token embeddings. Besides, we collect the first open-sourced intraoral image dataset IO150K, which comprises over 150k intraoral photos, and all photos are annotated by orthodontists using a human-machine hybrid algorithm. Experiments on IO150K demonstrate that our TeethSEG outperforms the state-of-the-art segmentation models on dental image segmentation.

Shopping through short video communities has become a new trend, but few currently understand users' purchase intention toward TikTok online courses. This research developed a purchasing intention model of TikTok online courses by extending the technology acceptance model. This study used a questionnaire survey method and collected 413 valid questionnaires. Partial least squares structural equation modeling (PLS-SEM) was adopted to test the hypotheses and found: (1) perceived usefulness and ease of use positively affect perceived value. Free trial negatively affects perceived cost. Perceived usefulness, perceived ease of use, and free trial indirectly affect purchase intention through two mediation variables; (2) live streaming proneness, live streaming engagement, and perceived value positively affect purchase intention, while the perceived cost will negatively affect purchase intention; (3) an exciting conclusion is that intelligent recommendation positively moderates the relationship between perceived value and live streaming engagement with purchase intention, but intelligent recommendation negatively moderates the relationship between perceived cost and purchase intention. These findings make theoretical contributions and provide managerial insights based on empirical results for short video community purchase intentions.

Heart Rate Variability (HRV) is proven to be related to critical cardiovascular diseases. However, HRV is related to other factors as well, among which the activity is the major one. A novel activity-aware HRV analysis method is proposed to improve its performance on daily life ECG data. First, activity types and intensity are obtained by processing 3-axis acceleration signals. Then heart rate data extracted from ECG signal are segmented according to the activity types and intensity. The heart rate segments are evaluated to determine its suitability for HRV analysis. The suitable segments are further processed to remove outliers and slow non-stationary trends caused by activity instability and other factors. Finally, HRV analysis is conducted on these suitable and processed segments, and the results are labeled with activity context information. Thus, HRV s under different activity contexts are obtained. The advantages of activity-aware HRV are: First, affection of activity on HRV stability is reduced. Second, we have gained HRV dynamics measure against activity types and intensity.