Saikat Dutta

I am a PhD scholar at IITB-Monash Research Academy. Here, I am working with Dr. Biplab Banerjee and Dr. Hamid Rezatofighi.

I worked as a Data Scientist at LG Ad Solutions for two years. Previously, I completed my MS (by Research) in Computer Science and Engineering (CSE), under the supervision of Dr. Anurag Mittal, from IIT Madras, India. Prior to that, I obtained my BE in CSE from Jadavpur University, India, where I worked with Dr. Sanjoy Kumar Saha. During my internship, I worked with Dr. Partha Pratim Roy at IIT Roorkee, India.

Email  /  LinkedIn  /  Google Scholar  /  Github

profile photo
Research

Most of my research works lie in the intersection of Computer Vision and Deep Learning. However, I have worked with Audio processing and Natural Language Processing as well.

Video Frame Interpolation
Non-linear Motion Estimation for Video Frame Interpolation using Space-time Convolutions
Saikat Dutta, Arulkumar Subramaniam, Anurag Mittal
CVPR Workshops, 2022
ReFIn: A Refinement Approach for Video Frame Interpolation
Saikat Dutta, Anurag Mittal
NeuriPS Workshops, 2021
Efficient space-time video super resolution using low-resolution flow and mask upsampling
Saikat Dutta, Nisarg A. Shah, Anurag Mittal
CVPR Workshops, 2021

Fake News Detection
A Heuristic-driven Uncertainty based Ensemble Framework for Fake News Detection in Tweets and News Articles
Sourya Dipta Das, Ayan Basak, Saikat Dutta
Neurocomputing, 2021
A heuristic-driven ensemble framework for COVID-19 fake news detection
Sourya Dipta Das, Ayan Basak, Saikat Dutta
AAAI Workshops, 2021

Bokeh Effect Rendering
Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image
Saikat Dutta, Sourya Dipta Das, Nisarg A. Shah, Anil Kumar Tiwari
CVPR Workshops, 2021
Depth-aware blending of smoothed images for bokeh effect generation
Saikat Dutta
Journal of Visual Communication and Image Representation, 2021

Misc. Image Restoration
DSRN: an efficient deep network for image relighting
Sourya Dipta Das, Nisarg A Shah, Saikat Dutta, Himanshu Kumar
ICIP, 2021
Fast deep multi-patch hierarchical network for nonhomogeneous image dehazing
Sourya Dipta Das, Saikat Dutta (Equal contribution)
CVPR Workshops, 2020

Music Emotion Recogntion
Recognition of emotion in music based on deep convolutional neural network
Rajib Sarkar, Sombuddha Choudhury, Saikat Dutta, Aneek Roy, Sanjoy Kumar Saha
Multimedia Tools and Applications, 2019
Emotion Based Categorization of Music Using Low Level Features and Agglomerative Clustering
Rajib Sarkar, Saikat Dutta, Aneek Roy, Sanjoy Kumar Saha
NCVPRIPG, 2017

Trajectory Analysis
An efficient approach for recognition and verification of on-line signatures using PSO
Saikat Dutta, Rajkumar Saini, Pradeep Kumar, Partha Pratim Roy
ACPR, 2017
Local behavior analysis for trajectory classification using graph embedding
Rajkumar Saini, Pradeep Kumar, Saikat Dutta, Partha Pratim Roy, Umapada Pal
ACPR, 2017

Other Research
Anomaly Detection In Retinal Images Using Multi-Scale Deep Feature Sparse Coding
Sourya Dipta Das, Saikat Dutta, Nisarg A Shah, Dwarikanath Mahapatra, Zongyuan Ge
ISBI, 2022
Robust Identification of Dense or Sparse Crowd Based on Classifier Fusion
Saikat Dutta, Soumya Kanti Naskar, Sanjoy Kumar Saha, Bhabatosh Chanda
PReMI, 2019
Reviewing duty
  • Journals
    • IEEE Transactions on Circuits and Systems for Video Technology
    • Expert Systems with Applications
    • Neurocomputing
    • Neural Networks
    • Pattern Recognition
    • Signal Processing: Image Communication
    • Multimedia Tools and Applications
    • Machine Vision and Applications
    • Journal of Visual Communication and Image Representation
  • Conferences/Workshops
    • WACV: 2022
    • ACM Multimedia: 2022, 2023
    • Mobile AI Workshop @ CVPR'21

Credits

I would like to thank Jon Barron for sharing this website template.