no code implementations • 21 Apr 2024 • Hasanul Mahmud, Kevin Desai, Palden Lama, Sushil K. Prasad
Our experimental results demonstrate that EncodeNet improves the accuracy of VGG16 from 92. 64% to 94. 05% on CIFAR-10 and RestNet20 from 74. 56% to 76. 04% on CIFAR-100.
1 code implementation • 26 Mar 2024 • Md Mushfiqur Azam, Kevin Desai
Egocentric human pose estimation aims to estimate human body poses and develop body representations from a first-person camera perspective.
no code implementations • 11 Mar 2024 • Hasanul Mahmud, Peng Kang, Kevin Desai, Palden Lama, Sushil Prasad
We present CBNet, a low-latency and energy-efficient DNN inference framework tailored for edge devices.
no code implementations • 26 Jun 2021 • Nihar Bendre, Kevin Desai, Peyman Najafirad
To overcome this problem, we propose a Multimodal Variational Auto-Encoder (M-VAE) which can learn the shared latent space of image features and the semantic space.
no code implementations • 15 May 2021 • Nihar Bendre, Kevin Desai, Peyman Najafirad
This results in achieving better understanding of complex questions and also provides reasoning as to why the module predicts a particular answer.