The conventional summarization model often fails to capture critical
inf...
Humans learn language via multi-modal knowledge. However, due to the
tex...
Compared to news and chat summarization, the development of meeting
summ...
Denoising diffusion models have shown remarkable potential in various
ge...
Adversarial training (AT) methods are effective against adversarial atta...
Extensive evidence has demonstrated that deep neural networks (DNNs) are...
Existing dialogue modeling methods have achieved promising performance o...
Knowledge distillation is an effective method to improve the performance...
The foundation model is not the last chapter of the model production
pip...
This paper presents a simple MLP-like architecture, CycleMLP, which is a...
Forms are a common type of document in real life and carry rich informat...
The field of face recognition (FR) has witnessed great progress with the...
This work presents a new fine-grained transparent object segmentation
da...
Scene text spotting aims to detect and recognize the entire word or sent...
Low-resolution text images are often seen in natural scenes such as docu...
In this paper, we introduce an anchor-box free and single shot instance
...
Distillation-based learning boosts the performance of the miniaturized n...
Scene text detection, an essential step of scene text recognition system...
Although deeper and larger neural networks have achieved better performa...
Incidental scene text spotting is considered one of the most difficult a...
The state-of-the-art of face recognition has been significantly advanced...