Generate caption on images using CNN Encoder- LSTM Decoder structure. This project is the second project of Udacity's Computer Vision Nanodegree and combines computer vision and machine translation ...

We present a simplified and novel fully convolutional neural network (CNN) architecture for semantic pixel-wise segmentation named as SCNet. Different from current CNN pipelines, proposed network uses ...

This paper presents a new model for short-term forecasting of electric vehicle (EV) fleet charging demand, designed to provide future demand predictions for day-ahead energy scheduling applications.

In this project, I intend to generate captions for images in the COCO 2014 dataset using a Encoder-Decoder model. The Microsoft Common Objects in COntext (MS COCO) dataset is a large-scale dataset for ...

Large language models (LLMs) have changed the game for machine translation (MT). LLMs vary in architecture, ranging from decoder-only designs to encoder-decoder frameworks. Encoder-decoder models, ...

Encoder-Decoder Architectures. Encoder-decoder architectures are a broad category of models used primarily for tasks that involve transforming input data into output data of a different form or ...