Deep Learning

Research project under Prof. Nisheeth Srivastava. Used a sequential Variational Autoencoder model for disentangling of time invariant content from dynamics in videos. Presently studying approaches for measuring similarities in videos using learned representations.

Project under Programming Club, IIT Kanpur. Studied various encoder-decoder based architectures for image captioning and implemented the model described in Show, Attend and Tell (Xu et al.2015) using Tensorflow. Used MS COCO dataset for training and evaluation.