output
20162024
most citedWhy my photos look sideways or upside down? Detecting Canonical Orientation of Images using Convolutional Neural Networks

15 citations

Showing cs.CVShow all

7 papers · 1 filter

cs.CV20229 cited

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…

cs.CV20219 cited

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…

cs.CV2021

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…

cs.CV20213 cited

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…

cs.CV2019

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…

cs.CV201715 cited

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…