Spatial and temporal saliency based four-stream network with multi-task learning for action recognition
Action recognition is a challenging video understanding task for the following two reasons:(i)
the complex video background impairs the recognition of desirable actions, and (ii) the …
the complex video background impairs the recognition of desirable actions, and (ii) the …
Robust hybrid learning for automatic teeth segmentation and labeling on 3D dental models
Automatic teeth segmentation and labeling on dental models are basic tasks in computer-
aided dentistry. Many existing works can achieve promising results in teeth segmentation …
aided dentistry. Many existing works can achieve promising results in teeth segmentation …
RGB oralscan video-based orthodontic treatment monitoring
Y Tian, H Fu, H Wang, Y Liu, Z Xu, H Chen, J Li… - Science China …, 2024 - Springer
Orthodontic treatment monitoring involves using current images and previous 3D models to
estimate the relative position of individual teeth before and after orthodontic treatment. This …
estimate the relative position of individual teeth before and after orthodontic treatment. This …
Transformer-based few-shot object detection in traffic scenarios
E Sun, D Zhou, Y Tian, Z Xu, X Wang - Applied Intelligence, 2024 - Springer
In few-shot object detection (FSOD), many approaches retrain the detector in the inference
stage, which is unrealistic in real applications. Moreover, high-quality region proposals are …
stage, which is unrealistic in real applications. Moreover, high-quality region proposals are …
Graph-based progressive fusion network for multi-modality vehicle re-identification
Vehicle re-identification (Re-ID) is a critical task in intelligent transportation, aiming to match
vehicle images of the same identity captured by non-overlapping cameras. However, it is …
vehicle images of the same identity captured by non-overlapping cameras. However, it is …
ImplantFormer: vision transformer-based implant position regression using dental CBCT data
Implant prosthesis is the most appropriate treatment for dentition defect or dentition loss,
which usually involves a surgical guide design process to decide the implant position …
which usually involves a surgical guide design process to decide the implant position …
A revised approach to orthodontic treatment monitoring from oralscan video
Y Tian, G Jian, J Wang, H Chen, L Pan… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
Research on orthodontic treatment monitoring from oralscan video is a new direction in
dental digitalization. We designed an approach to reconstruct, segment, and estimate the …
dental digitalization. We designed an approach to reconstruct, segment, and estimate the …
A tooth surface design method combining semantic guidance, confidence, and structural coherence
Research on tooth surface design based on deep neural networks has recently achieved
progress in terms of both accuracy and execution efficiency. However, unrealistic outputs …
progress in terms of both accuracy and execution efficiency. However, unrealistic outputs …
Automatic tooth segmentation from 3d dental model using deep learning: a quantitative analysis of what can be learnt from a single 3d dental model
A Jana, HM Subhash… - … Symposium on Medical …, 2023 - spiedigitallibrary.org
3D tooth segmentation is an important task for digital orthodontics. Several Deep Learning
methods have been proposed for automatic tooth segmentation from 3D dental models or …
methods have been proposed for automatic tooth segmentation from 3D dental models or …
MobileACNet: ACNet-based lightweight model for image classification
Lightweight CNN models aim to extend the application of deep learning from conventional
image classification to mobile edge device-based image classification. However, the …
image classification to mobile edge device-based image classification. However, the …