activity
20172021
most citedAdversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

7 citations · 14 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV20217 cited

Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

Shasha Li, Abhishek Aich, Shitong Zhu +4

When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because,…

cs.CV20215 cited

Spatio-Temporal Representation Factorization for Video-based Person Re-Identification

Abhishek Aich, Meng Zheng, Srikrishna Karanam +3

Despite much recent progress in video-based person re-identification (re-ID), the current state-of-the-art still suffers from common real-world challenges such as appearance simila…

eess.IV2021

Deep Quantized Representation for Enhanced Reconstruction

Akash Gupta, Abhishek Aich, Kevin Rodriguez +2

While machine learning approaches have shown remarkable performance in biomedical image analysis, most of these methods rely on high-quality and accurate imaging data. However, col…

cs.CV2021

Elastic Weight Consolidation (EWC): Nuts and Bolts

Abhishek Aich

In this report, we present a theoretical support of the continual learning method \textbf{Elastic Weight Consolidation}, introduced in paper titled `Overcoming catastrophic forgett…

cs.CV20202 cited

ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation

Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury

Existing works address the problem of generating high frame-rate sharp videos by separately learning the frame deblurring and frame interpolation modules. Most of these approaches…

eess.IV2020

Non-Adversarial Video Synthesis with Learned Priors

Abhishek Aich, Akash Gupta, Rameswar Panda +3

Most of the existing works in video synthesis focus on generating videos using adversarial learning. Despite their success, these methods often require input reference frame or fai…