Cardiac MRI segmentation is a significant research area in medical image processing, holding immense clinical and scientific importance in assisting the diagnosis and treatment of heart diseases. Currently, existing cardiac MRI segmentation ...

• The ConvNext block and U-shaped structure were successfully integrated and applied to the segmentation of cardiac MRI images.
• Input stem and attention modules are incorporated into ConvNextUNet, enabling the model to achieve a more ...

The majority of supervised models estimate optical flow through minimizing the numerical difference between the predicted flow and the ground truth, resulting in the loss of positional and geometric characteristics of the calculated flow fields. ...

• A loss function incorporates epipolar geometry into supervised optical flow models.
• More interpretable and clear mathematical meaning for optical flow estimation.
• A lightweight recurrent neural network for optical flow calculation.

The physics-based optical flow (PBOF) model was derived from typical flow visualizations and it provided a more solid physical foundation for optical flow calculation. However, like many recent variational optical flow methods, it is ...

• More solid physical foundation for optical flow estimation.
• A linear ...

In this paper, we proposed a novel motion model with Helmholtz decomposition for complex fluid flows in a filtering-based optical flow framework, where the optimization of the regularization term is treated as a filtering process, and different motion ...

Temporal action detection is an important yet challenging task in video understanding task. Temporal action proposals generation is a common module in action detection, and it effects the performance of action detection greatly. The module ...

Echocardiogram illustrates what the capacity it owns of detecting the global and regional functions of the heart. With obvious benefits of non-invasion, visuality and mobility, it has become an indispensable technology for clinical evaluation of ...

Optical flow computation for video under the dynamic illumination is a challenging issue in video multimedia applications. In this paper, we solve this issue by introducing an illumination-invariant framework for variational optical flow estimation. It ...

Accurate optical flow estimation with the frequency-domain regularization is a challenging problem in computer vision. In this paper, we solve this issue by introducing a novel optical flow method related to the frequency domain that uses TV-wavelet ...

We present a novel optical flow estimation framework that reinterprets most popular algorithms (e.g., the Horn–Schunck model, PDE-based models, TV-based models, and nonlocal-based models) from an iterative filtering perspective. Different ...

A variational solution of the physics-based optical flow equation is studied for extraction of high-resolution velocity fields from flow visualization images. The solution to preserve discontinuities in a fluid velocity field is mathematically ...

Differential Power Analysis against AES proved to be effective, with use mask techniques, we can truncate the relevance and defense DPA attacks successfully. In this paper, we introduce a new mean called DFA (Differential Fault Attack), DFA has ...

Due to the numerous important applications of face images, such as long-distance video surveillance and identity verification, face hallucination has been an active research topic in the last decade. This paper makes a survey of approaches to high ...

Railway condition monitoring is one of crucial factors to ensure safe and cost-effectiveness of train operation. A fiber Bragg grating sensors based real-time train wheel condition monitoring system has been developed and reported by our team. In the ...

To measure the temperature profile of various critical parts on a train bogie to fore-warn the train drivers the potential failures in those mechanical parts, such as the axle and motor bearing, gear box bearing, and braking mechanisms, which could go ...