Publications
2023
-
EcoVal: An Efficient Data Valuation Framework for Machine Learning
Ayush K Tarun, Vikram S Chundawat, Murari Mandal, Hong Ming Tan, Bowei Chen, Mohan Kankanhalli
Arxiv
[Paper]
-
Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation
Yash Sinha, Murari Mandal, Mohan Kankanhalli
Arxiv
[Paper]
-
Deep Regression Unlearning
AK Tarun, VS Chundawat, Murari Mandal, Mohan Kankanhalli
40th International Conference on Machine Learning (ICML-2023), Honolulu, Hawaii, Jul 23 - 29, 2023 [CORE A*]
[Paper], [Source Code]
-
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
VS Chundawat, AK Tarun, Murari Mandal, Mohan Kankanhalli
37th AAAI Conference on Artificial Intelligence (AAAI-2023), Washington, DC, Feb 7 - Feb 14, 2023 [Acceptance Rate - 19.6%] [CORE A*]
[Paper], [Source Code], [Poster]
-
Zero-Shot Machine Unlearning
VS Chundawat, AK Tarun, Murari Mandal, Mohan Kankanhalli
IEEE Transactions on Information Forensics and Security, 2023 [IF: 7.23]
[Paper], [Source Code]
-
Fast Yet Effective Machine Unlearning
AK Tarun, VS Chundawat, Murari Mandal, Mohan Kankanhalli
IEEE Transactions on Neural Networks and Learning Systems, 2023 [IF: 14.25]
[Paper], [Source Code]
-
Error Maximizing Anti-Sample Generation for Fast Machine Unlearning
AK Tarun, VS Chundawat, Murari Mandal, Mohan Kankanhalli
AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI), AAAI Workshops-2023 [CORE A*]
[Poster]
-
Efficient Neural Architecture Search for Emotion Recognition
Monu Verma, Murari Mandal, Satish Kumar Reddy, Yashwanth Reddy Meedimale, Santosh Kumar Vipparthi
Expert Systems with Applications, Elsevier 2023 [IF: 8.67]
[Paper]
2022
-
A Universal Metric for Robust Evaluation of Synthetic Tabular Data
VS Chundawat, AK Tarun, Murari Mandal, Mukund Lahoti, Pratik Narang
IEEE Transactions on Artificial Intelligence, 2022
[Paper], [Source Code]
-
Captionomaly: A Deep Learning Toolbox for Anomaly Captioning in Social Surveillance Systems
Adit Goyal, Murari Mandal, Vikas Hassija, Vinay Chamola, Moayad Aloqaily
IEEE Transactions on Computational Social Systems, 2022 [IF: 4.75]
[Paper], [Source Code]
-
Neural Architecture Search for Image Dehazing
Murari Mandal, Yashwanth Reddy Meedimale, M. Satish Kumar Reddy, Santosh Kumar Vipparthi
IEEE Transactions on Artificial Intelligence, 2022
[Paper]
2021
-
DroneSegNet: Robust Aerial Semantic Segmentation for UAV-based IoT Applications
AS Chakravarthy, Soumendu Sinha, Pratik Narang ,Murari Mandal, Vinay Chamola, F.R. Yu
IEEE Transactions on Vehicular Technology, 2021 [IF: 6.24]
[Paper]
-
AutoMER: Spatiotemporal Neural Architecture Search for Microexpression Recognition
Monu Verma, M Satish Reddy, Yashwanth Reddy, Murari Mandal, Santosh Kumar Vipparthi
IEEE Transactions on Neural Networks and Learning Systems, 2021 [IF: 14.25]
[Paper]
-
3DCD: Scene Independent End-to-End Spatiotemporal Feature Learning Framework for Change Detection in Unseen Videos
Murari Mandal, Vansh Dhar, Abhishek Mishra, Santosh Kumar Vipparthi, Mohamed Abdel-Mottaleb
IEEE Transactions on Image Processing, 2021 [IF: 11.04]
[Paper]
-
An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs
Murari Mandal, Santosh Kumar Vipparthi
IEEE Transactions on Intelligent Transportation Systems, 2021 [IF: 9.55]
[Paper]
-
Domain-Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing
Aditya Mehta, Harsh Sinha, Murari Mandal, Pratik Narang
IEEE Winter Conference on Applications of Computer Vision (WACV-2021), 2021 [CORE A]
[Paper], [Video]
-
Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement
Prateek Garg, Murari Mandal, Pratik Narang
AAAI Conference on Artificial Intelligence (AAAI-2021), Student Abstract, Vancouver, Canada, 2021 [CORE A*]
[Paper], [Source Code]
-
Learning to Enhance Visual Quality via Hyperspectral Domain Mapping
Harsh Sinha, Aditya Mehta, Murari Mandal, Pratik Narang
AAAI Conference on Artificial Intelligence (AAAI-2021), Student Abstract, Vancouver, Canada 2021 [CORE A*]
[Paper]
-
AI-enabled Object Detection in UAVs: Challenges, Design Choices, and Research Directions
Ayush Jain, Rohit R, Pratik Narang, Murari Mandal, Vinay Chamola, Richard Yu, Mohsen Guizani
IEEE Network, 2021 [IF: 10.29]
[Paper], [Source Code]
-
AgriSegNet: Deep Aerial Semantic Segmentation Framework for IoT-assisted Precision Agriculture
Tanmay Anand, Soumendu Sinha, Murari Mandal, Vinay Chamola, Fei Richard Yu
IEEE Sensors Journal, 2021 [IF: 4.33]
[Paper]
-
TheiaNet: Towards fast and inexpensive CNN design choices for image dehazing
Aryan Mehra, Pratik Narang, Murari Mandal
Journal of Visual Communication and Image Representation, 2021 [IF: 2.89]
[Paper]
2020
-
Scene Independency Matters: An Empirical Study of Scene Dependent and Scene Independent Evaluation for CNN based Change Detection
Murari Mandal, Santosh Kumar Vipparthi
IEEE Transactions on Intelligent Transportation Systems, 2020 [IF: 9.55]
[Paper]
-
MOR-UAV: A Benchmark Dataset and Baselines for Moving Object Recognition in UAV Videos
Murari Mandal, Lav Kush Kumar, Santosh Kumar Vipparthi
28th ACM International Conference on Multimedia (ACMMM-2022), Seattle WA USA, 2020 [CORE A*]
[Paper] [Dataset]
-
MotionRec: A Unified Deep Framework for Moving Object Recognition
Murari Mandal, Lav Kush Kumar, Mahipal Singh Saran, Santosh Kumar Vipparthi
IEEE Winter Conference on Applications of Computer Vision (WACV-2020), Snowmass Village, CO, USA, 2020 [CORE A]
[Paper], [Source Code], [Dataset], [Annotations]
-
AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data
Murari Mandal, Manal Shah, Prashant Meena, Sanhita Devi, Santosh Kumar Vipparthi
IEEE Geoscience and Remote Sensing Letters, 2020 [IF: 5.34]
[Paper]
-
ReViewNet: A fast and resource optimized network for enabling safe autonomous driving in hazy weather conditions
Aryan Mehra, Murari Mandal, Pratik Narang, Vinay Chamola
IEEE Transactions on Intelligent Transportation Systems, 2020 [IF: 9.55]
[Paper]
-
ISDNet: AI-enabled Instance Segmentation of Aerial Scenes for Smart Cities
Prateek Garg, AS Chakravarthy, Murari Mandal, Pratik Narang, Vinay Chamola, Mohsen Guizani
ACM Transactions on Internet Technology, 2020 [IF: 3.98]
[Paper]
-
HIDeGan: A Hyperspectral-Guided Image Dehazing GAN
Harsh Sinha, Aditya Mehta, Pratik Narang, Murari Mandal
CVPR Workshops (CVPRW-2020), Seattle, WA, USA, 2020 [CORE B]
[Paper], [Source Code] [Video]
2019
-
ANTIC: ANTithetic Isomeric Cluster Patterns for Medical Image Retrieval and Change Detection
Murari Mandal, Santosh Kumar Vipparthi, Mallika Chaudhary, Subramanian Murala, Anil Balaji Gonde, S. K. Nagar
IET Computer Vision, 2019 [IF:1.48]
[Paper]
-
RADAP: Regional Adaptive Affinitive Patterns with Logical Operators for Facial Expression Recognition
Murari Mandal, Monu Verma, Sonakshi Mathur, Santosh Kumar Vipparthi, Subrahmanyam Murala, D. Kranthi Kumar
IET Image Processing, 2019 [IF:1.77]
[Paper]
-
SSSDET: Simple Short and Shallow Network for Resource Efficient Vehicle Detection in Aerial Scenes
Murari Mandal, Manal Shah, Prashant Meena, Santosh Kumar Vipparthi
26th IEEE International Conference on Image Processing (ICIP-2019), Taipei, Taiwan, 2019 [CORE B]
[Paper]
-
3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection
Murari Mandal, Vansh Dhar, Abhishek Mishra, Santosh Kumar Vipparthi
IEEE Signal Processing Letters, 2019 [IF:3.2]
[Paper]
-
Challenges in Time-Stamp Aware Anomaly Detection in Traffic Videos
Kuldeep Marotirao Biradar, Ayushi Gupta, Murari Mandal, Santosh Kumar Vipparthi
CVPR Workshops (CVPRW-2019), Long Beach, CA, USA, 2019 [CORE B]
[Paper]
2018
-
CANDID: Robust Change Dynamics and Deterministic Update Policy for Dynamic Background Subtraction
Murari Mandal, Prafulla Saxena, Santosh Kumar Vipparthi, Subrahmanyam Murala
24th IEEE International Conference on Pattern Recognition (ICPR-2018), Beijing, China, 2018 [CORE B]
[Paper]
Doctoral Dissertation
Moving Object Detection for Visual Data Analytics in Conventional and Aerial View
The research in this thesis focuses on the need of deep learning frameworks for MOD in conventional and aerial scenes. These models and frameworks would be very useful in strategic solution and implementation for video analytics in both the conventional and aerial view-based visual surveillance.