Research/Publications
I'm interested in computer vision, deep learning, and machine learning. Much
of my research is about working with images/videos in the domain of generative modeling.
|
|
DF-Platter: Multi-subject Heterogeneous Deepfake Dataset
Kartik Narayan*,
Harsh Agarwal*,
Kartik Thakral,
Surbhi Mittal,
Mayank Vatsa,
Richa Singh
CVPR , 2023
In this research, we emulate the real-world scenario of deepfake generation and spreading, and
propose the DF-Platter dataset which contains (i) both low-resolution and high-resolution deepfakes
generated using multiple generation techniques, (ii) single-subject and multiple-subject deepfakes.
The results demonstrate a significant performance reduction in the deepfake detection task on
low-resolution deepfakes and show that the existing techniques fail drastically on multiple-subject
deepfakes.
|
|
DeSI: Deepfake Source Identifier for Social Media
Kartik Narayan*,
Harsh Agarwal*,
Surbhi Mittal,
Kartik Thakral,
Suman Kundu,
Mayank Vatsa,
Richa Singh
CVPR Workshops, 2022
paper
/
web-portal
/
poster
/
demo
video
We develop an algorithm to find the source/propagator of tweets with deepfake/manipulated
images/videos relevant to a given text query. The result is shown in form of a force-directed graph
which gives temporal insight into the spread pattern and also identifies the volatile nodes in the
network by predicting the virality of tweets.
|
|
DeePhy: On Deepfake Phylogeny
Kartik Narayan,
Harsh Agarwal,
Kartik Thakral,
Surbhi Mittal,
Mayank Vatsa,
Richa Singh
International Joint Conferece on Biometrics (IJCB), 2022
paper
/
database
/
poster
We proposed the idea of DeepFake Phylogeny and a complementary dataset DeePhy. The paper shows the
need to evolve the research of model attribution of deepfakes and facilitates advancements in real
life scenarios of plagiarism detection, forgery detection, and reverse engineering of deepfakes.
|
|
Using Epidemic Modelling, Machine Learning and Control Feedback Strategy for Policy
Management of COVID-19
Kartik Narayan,
Heena Rathore,
Faycal Znidi
IEEE Access, 2022
paper
/
code
We propose a threshold mechanism for policy control by analyzing the SIR model and estimating the
optimal parameters. Our work helps keep the economic impact of a pandemic under control and also
helps in predicting the approximate duration of the lockdwon.
|
|
Leveraging ambient sensing for the estimation of curiosity-driven human crowd
Anirban Das,
Kartik Narayan,
Suchetana Chakraborty
IEEE Systems Conference (SysCon), 2022
paper
We predicted the curious crowd attracted to an object by measuring it's spatiotemporal significance.
The work utilizes a set of passive sensors and wireless signal properties for the estimation.
|
|