Image Captioning using CNN and RNN in Torch

Image Captioning using CNN and RNN in Torch

A blind data augmentation method was developed and used in the project, which resulted in better sentence generation than state-of-the-art.

Artificial Intelligence

  • 0 Collaborators

  • 1 Followers

    Follow

Description

In my Btech mini project, Sayeem Shaikh, a PhD scholar; Maharshi Vyas, a BTech student and I were working on the Image captioning project using CNNs and RNNs in Torch. We reproduced the Andrej Karpathy results first from his paper. After that, we were tickling with the architecture to work on more data. During the project, the blind data augmentation method developed by us resulted in better BLEU score on 4-gram model than Karpathy et al.'s paper. By blind augmentation, we mean that there was no prior to start with.

Mentor- Manjunath V. Joshi, Professor, DA-IICT, Gandhinagar

Medium screenshot from 2017 08 10 23 09 03

Vaibhav P. created project Image Captioning using CNN and RNN in Torch

Medium f9809cc4 e202 4a54 b457 ac1d9c1fc437

Image Captioning using CNN and RNN in Torch

In my Btech mini project, Sayeem Shaikh, a PhD scholar; Maharshi Vyas, a BTech student and I were working on the Image captioning project using CNNs and RNNs in Torch. We reproduced the Andrej Karpathy results first from his paper. After that, we were tickling with the architecture to work on more data. During the project, the blind data augmentation method developed by us resulted in better BLEU score on 4-gram model than Karpathy et al.'s paper. By blind augmentation, we mean that there was no prior to start with.

Mentor- Manjunath V. Joshi, Professor, DA-IICT, Gandhinagar

No users to show at the moment.