As large language models continue to develop in the field of AI, text
ge...
Structured text extraction is one of the most valuable and challenging
a...
Visual information extraction (VIE), which aims to simultaneously perfor...
Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled dat...
The recent large-scale Contrastive Language-Image Pretraining (CLIP) mod...
Ramp merging is a typical application of cooperative intelligent
transpo...
Semantic segmentation based on sparse annotation has advanced in recent
...
Lane detection is one of the fundamental modules in self-driving. In thi...
According to the requirement of general static obstacle detection, this ...
Most commercially available optical see-through head-mounted displays
(O...
Convolutional operations have two limitations: (1) do not explicitly mod...
Building applications that perceive the world around them is challenging...
Recently, Neural Architecture Search (NAS) has successfully identified n...
We propose a method for learning CNN structures that is more efficient t...