15 citations
- Indian Institute of Technology BombayIN1 paper
- Indian Institute of Technology GuwahatiIN1 paper
- Indian Institute of Technology KanpurIN1 paper
- Newcastle UniversityGB1 paper
- Sikkim Manipal UniversityIN1 paper
- University of Newcastle AustraliaAU1 paper
- University of North TexasUS1 paper
- University of WolverhamptonGB1 paper
7 papers · 1 filter
PrivPAS: A real time Privacy-Preserving AI System and applied ethics
Harichandana B S S, Vibhav Agarwal, Sourav Ghosh +3
With 3.78 billion social media users worldwide in 2021 (48% of the human population), almost 3 billion images are shared daily. At the same time, a consistent evolution of smartpho…
A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics
Prasen Kumar Sharma, Arun Abraham, Vikram Nelvoy Rajendiran
Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recen…
FONTNET: On-Device Font Understanding and Prediction Pipeline
Rakshith S, Rishabh Khurana, Vibhav Agarwal +2
Fonts are one of the most basic and core design concepts. Numerous use cases can benefit from an in depth understanding of Fonts such as Text Customization which can change text in…
On-Device Document Classification using multimodal features
Sugam Garg, Harichandana, Sumit Kumar
From small screenshots to large videos, documents take up a bulk of space in a modern smartphone. Documents in a phone can accumulate from various sources, and with the high storag…
Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network
Abhay Kumar, Nishant Jain, Chirag Singh +1
This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (S…
Why my photos look sideways or upside down? Detecting Canonical Orientation of Images using Convolutional Neural Networks
Kunal Swami, Pranav P. Deshpande, Gaurav Khandelwal +1
Image orientation detection requires high-level scene understanding. Humans use object recognition and contextual scene information to correctly orient images. In literature, the p…