activity
20162023
most citedHierarchical Representation Learning for Kinship Verification

81 citations · 262 across the 26 of their papers we have counts for

collaborators
Showing 2020Show all

12 papers · 1 filter

cs.CV2020

Age Gap Reducer-GAN for Recognizing Age-Separated Faces

Daksha Yadav, Naman Kohli, Mayank Vatsa +2

In this paper, we propose a novel algorithm for matching faces with temporal variations caused due to age progression. The proposed generative adversarial network algorithm is a un…

cs.CV2020

WaveTransform: Crafting Adversarial Examples via Input Decomposition

Divyam Anshumaan, Akshay Agarwal, Mayank Vatsa +1

Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images ha…

cs.CV2020

Attack Agnostic Adversarial Defense via Visual Imperceptible Bound

Saheb Chhabra, Akshay Agarwal, Richa Singh +1

The high susceptibility of deep learning algorithms against structured and unstructured perturbations has motivated the development of efficient adversarial defense algorithms. How…

cs.CV2020

MixNet for Generalized Face Presentation Attack Detection

Nilay Sanghvi, Sushant Kumar Singh, Akshay Agarwal +2

The non-intrusive nature and high accuracy of face recognition algorithms have led to their successful deployment across multiple applications ranging from border access to mobile…

cs.CV2020

Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings

Mehak Gupta, Vishal Singh, Akshay Agarwal +2

Presentation attacks are posing major challenges to most of the biometric modalities. Iris recognition, which is considered as one of the most accurate biometric modality for perso…

cs.CV2020

Unravelling Small Sample Size Problems in the Deep Learning World

Rohit Keshari, Soumyadeep Ghosh, Saheb Chhabra +2

The growth and success of deep learning approaches can be attributed to two major factors: availability of hardware resources and availability of large number of training samples.…