Abstract: This paper presents DSConvNet, a novel architecture based on depthwise separable convolutional blocks for efficient multi-class image classification. Despite progress in compact ...

Abstract: Artificial intelligence has been more and more used in recent years, including computer-aided diagnosis systems. The published scientific papers increased exponentially, making it hard to ...

Automatically describing an image with a natural language has been an emerging challenge in both fields of computer vision and natural language processing. In this paper, we present Long Short-Term ...

This repository contains the code for the paper "MSSPlace: Multi-Sensor Place Recognition with Visual and Text Semantics". High-level overview of the proposed multimodal MSSPlace method. The MSSPlace ...

Stable Diffusion is a latent text-to-image diffusion model. For more efficiency and speed on GPUs, we highly recommended installing the xformers library. Tested on ...