Dr. Mridula Verma
Assistant Professor
vmridula(at)idrbt(dot)ac(dot)in
Educational Qualifications
- Ph.D. in Computer Science and Engineering from Indian Institute of Technology (BHU) in 2018
- M.Tech. in Computer Science and Engineering from Indian Institute of Technology, Roorkee in 2009
- B.E. in Computer Science and Engineering from Pt. Ravishankar Shukla University, Raipur in 2006.
Research Interests
- Artificial Intelligence & Machine Learning
- Intersection of Natural Language Processing (NLP) & Deep Learning, Financial NLP
- Secure and Private Machine Learning, Federated Learning, Privacy-preserving Machine Learning.
- MLOps and ModelOps
Professional Experience
- Worked as Assistant Professor in Delhi Technological University from September 2012 to June 2013
- Worked as Assistant Professor in Galgotia College of Engineering and Technology from July 2010 to December 2011.
Achievements
- IIT (BHU) Institute Fellowship for PhD from July 2013 to January 2018
- GATE Scholarship from August 2007 to July 2009
- Merit Scholarship from Bhilai Steel Plant, SAIL for Bachelors in Engineering from 2002 to 2006.
Ph.D. Guidance
- Hemraj Singh (with Dr Ramalingaswamy Cheruku, NITW), “Video Salient Object Detection using Lightweight Deep Learning Approaches”. In progress since 2020.
- Zarka Bashir (with Prof C. Krishna Mohan, IIT Hyderabad), “Federated Learning”. In progress since 2021.
Memberships
- Association for Computing Machinery
- The Institution of Engineers (India)
Recent Publications
Journals
Conferences
Journals
- Hemraj Singh, Mridula Verma and Ramalingaswamy Cheruku (2023), “Novel Dilated Separable Convolution Networks for Efficient Video Salient Object Detection in the Wild”. IEEE Transactions on Instrumentation and Measurement (Accepted). Impact Factor: 5.6.
- Mridula Verma and K K Shukla (2020), Convergence analysis of accelerated proximal extra-gradient method with applications. Neurocomputing, volume 388, pp 288-300. Impact Factor: 4.438.
- D R Sahu, Ariana Pitea, Mridula Verma (2020), A New Iteration technique for nonlinear operators as concerns convex programming and feasibility problems. Numerical Algorithms, volume 83, pp 421–449, Impact Factor: 2.064.
- Mridula Verma and K K Shukla (2017), “A New Accelerated Proximal Technique for Regression with High-dimensional Datasets”, Knowledge and Information Systems (KAIS), Vol. 53, Issue 2, pp. 423–438. Acceptance Rate < 19.1%, IF: 2.004
- Mridula Verma and K K Shukla (2017), “A New Accelerated Proximal Gradient Technique for Regularized Multitask Learning Framework”, In Pattern Recognition Letters, Vol. 95, pp. 98-103, 2017, ISSN 0167-8655, IF: 1.995
- Mridula Verma, D R Sahu and K K Shukla (2017), “VAGA: A Novel Viscosity-based Accelerated Gradient Algorithm: Convergence Analysis and Application to Multitask Regression. Applied Intelligence”, IF: 1.904
- Mridula Verma, S Asmita and K K Shukla (2016), “A Regularized Ensemble of Classifiers for Sensor Drift Compensation”. IEEE Sensors Journal, Vol. 16, No. 5, pp. 1310-1318, Acceptance Rate < 30%, Impact Factor: 2.512.
Conferences
- Hemraj Singh, Mridula Verma, and Ramalingaswamy Cheruku (2023), DSNet: Efficient Lightweight Model for Video Salient Object Detection for IoT and WoT Applications, In Companion Proceedings of the ACM Web Conference 2023 (WWW ’23 Companion). CORE Ranking: A*
- Hemraj Singh, Mridula Verma, Ramalingaswamy Cheruku (2022), VS-Net: Multiscale Spatiotemporal Features for Lightweight Video Salient Document Detection, Proceedings of IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI), Macao, China, 2022, pp. 1307-1311. CORE Ranking: B
- Sasubilli, S., Verma, M. (2022). InFi-BERT 1.0: Transformer-Based Language Model for Indian Financial Volatility Prediction. In: et al. Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2022. Communications in Computer and Information Science, vol 1753. Springer, Cham. CORE Ranking: A
- Prayas Jain, Mridula Verma, K K Shukla (2020), Convergence Rate Analysis of Viscosity Approximation based Gradient Algorithms, Proceedings of International Joint Conference on Neural Networks (IJCNN 2020), Glasgow (UK), CORE Ranking: A
- Mridula Verma and K K Shukla (2017), “Fast Multi-Modal Unified Sparse Representation Learning”, Proceedings of ACM International Conference on Multimedia Retrieval, June 2017. (Conference Ranked #1 in the field of Multimedia Retrieval), Bucharest, Romania. CORE Ranking: B
- Mridula Verma, Prayas Jain, K K Shukla (2016), “A New Faster First Order Iterative Scheme for Sparsity-based Multitask Learning”, Proceedings of 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary, pp. 1603-1608. CORE Ranking: B
- Ramashish Gaurav, Mridula Verma, K K Shukla (2016), “Informed Multimodal Latent Subspace Learning via Supervised Matrix Factorization”, Proceedings of Tenth Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP 2016), IIT Guwahati. (Acceptance Rate: 22%).