It is important to clarify: we do not use VLMs to drive the robot. Using a heavy cloud model to steer in real time would ...

Abstract: In generic object detection, detectors are often susceptible to foreground objects and background regions that share similar appearances. In this paper, we propose a novel discriminative ...

What if technology could bridge the gap between spoken language and sign language, empowering millions of people to communicate more seamlessly? With advancements in deep learning, this vision is no ...

Abstract: Traditional deep-learning-based object detection networks often resize images during the data preprocessing stage to achieve a uniform size and scale in the feature map. Resizing is done to ...

July 6th 2022 will be marked down as a landmark in AI history because it was on this day when YOLOv7 was released. Ever since its launch, the YOLOv7 has been the hottest topic in the Computer Vision ...

Wheat stripe rusts are responsible for the major reduction in production and economic losses in the wheat industry. Thus, accurate detection of wheat stripe rust is critical to improving wheat quality ...

In this paper, we present a novel Dynamic DETR (Detection with Transformers) approach by introducing dynamic attentions into both the encoder and decoder stages of DETR to break its two limitations on ...

1 School of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China. 2 School of Electronic Engineering and Intelligentization, Dongguan University of Technology, Dongguan, China. 3 ...