Motion-based controllable video generation offers the potential for creating captivating visual
content. Existing methods typically necessitate model training to encode particular motion …

The text-to-video (T2V) generation models, offering convenient visual creation, have recently
garnered increasing attention. Despite their substantial potential, the generated videos may …

As computer vision continues to advance and finds widespread applications across various
domains, the need for interpretability in deep learning models becomes paramount. Existing …

The trade-off between cost and performance has been a longstanding and critical issue for
deep neural networks. One key factor affecting the computational cost is the width of each …

In this work, we propose MetaScript, a novel Chinese content generation system designed
to address the diminishing presence of personal handwriting styles in the digital …

Text-to-image (T2I) diffusion/flow models have drawn considerable attention recently due to
their remarkable ability to deliver flexible visual creations. Still, high-resolution image …

Recent advancements in image relighting models, driven by large-scale datasets and pre-trained
diffusion models, have enabled the imposition of consistent lighting. However, video …

Background We investigated the superiority of the 8th edition of the tumor-node-metastasis (TNM)
system for patients in China with gastric cancer. Methods The survival outcomes of …

Background The optimal extent of gastrectomy for middle-third gastric cancer remains
controversial. In our study, the short-term effects and longer-term survival outcomes of distal …

Background The relationship between the number of harvested lymph nodes (HLNs) and
prognosis of gastric cancer patients without an involvement of lymph nodes has not been well-…