Official implementation of the ICASSP-2022 paper "Text2Poster: Laying Out Stylized Texts on Retrieved Images"

Implementation of Transformer Encoder Decoder Architecture for Video Predictions

Using to predict the highway traffic speed

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs

Implementation of Convolutional Encoder Decoder Network for short term (0 - 2 hours) weather forecasting.

Sequence-to-Sequence Generative Model for Sequential Recommender System

Random lyrics generator.

Neural Machine Translation using LSTMs and Attention mechanism. Two approaches were implemented, models, one without out attention using repeat vector, and the other using encoder decoder architecture and attention mechanism.

Generating Video Caption Using LSTM

Code for "ObscureNet: Learning Attribute-invariant Latent Representation for Anonymizing Sensor Data", ACM/IEEE IoTDI 2021

Image captioning with a benchmark of CNN-based encoder and GRU-based inject-type (init-inject, pre-inject, par-inject) and merge decoder architectures

TransRUPNet for Improved Out-of-Distribution Generalization in Polyp Segmentation (IEEE EMBC)

Repository containing the codes used for the development of a heart sound prediction system using convolutional neural networks (CNN) for semantic segmentation.

The project aims at predicting the prices of Open and Close prices in intraday stock market for next 5 minute window

Implementation of GNNs for Visual Question Answering task in PyTorch

Shadow Detection using RESNET Encoder Decoder Network

Automatic Image Captioning using Deep Learning

This is the PyTorch-based model implementation of the paper "Listen, Attend and Spell", an attention-based encoder-decoder neural model for speech utterance transcription.

My implementation of autoencoders