no code implementations • 19 Apr 2024 • Aravinda Reddy PN, Raghavendra Ramachandra, Krothapalli Sreenivasa Rao, Pabitra Mitra
Face-morphing attacks are a growing concern for biometric researchers, as they can be used to fool face recognition systems (FRS).
no code implementations • 17 Mar 2024 • Suryam Arnav Kalra, Arindam Biswas, Pabitra Mitra, BISWAJIT BASU
We prune recurrent networks such as RNNs and LSTMs, maintaining a large spectral gap of the underlying graphs and ensuring their layerwise expansion properties.
no code implementations • 19 Feb 2024 • Shubhi Shukla, Manaar Alam, Pabitra Mitra, Debdeep Mukhopadhyay
Machine learning, with its myriad applications, has become an integral component of numerous technological systems.
1 code implementation • 19 Oct 2023 • Aravinda Reddy PN, K. Sreenivasa Rao, Raghavendra Ramachandra, Pabitra Mitra
We present a novel face swapping method using the progressively growing structure of a pre-trained StyleGAN.
no code implementations • 12 Oct 2023 • Monnie Parida, Manjira Sinha, Anupam Basu, Pabitra Mitra
According to the study, there was a noticeable correlation between reading speed and reading errors.
no code implementations • 1 Aug 2022 • Shubhi Shukla, Manaar Alam, Sarani Bhattacharya, Debdeep Mukhopadhyay, Pabitra Mitra
In this paper, as a separate case study, we demonstrate that a DL model secured with differential privacy (a popular countermeasure against MIA) is still vulnerable to MIA against an adversary exploiting Class Leakage.
no code implementations • 15 Feb 2022 • Manashi Chakraborty, Aritri Chakraborty, Prabir Kumar Biswas, Pabitra Mitra
The data relation loss enables learning better texture representation which is pivotal for a texture rich dataset such as iris.
no code implementations • 29 Sep 2021 • BITHIKA PAL, Arindam Biswas, Pabitra Mitra, BISWAJIT BASU
Subsequently, with the loss of Ramanujan graph property, accuracy begins to reduce sharply.
no code implementations • 29 Sep 2021 • Swarnava Das, Pabitra Mitra, Debasis Ganguly
This means that an adversarial crafted image which is sufficiently close (visually indistinguishable) to its representative class can often be misclassified to be a member of a different class.
no code implementations • 9 Sep 2021 • Hareesh Mandalapu, Aravinda Reddy P N, Raghavendra Ramachandra, K Sreenivasa Rao, Pabitra Mitra, S R Mahadeva Prasanna, Christoph Busch
This new dataset contains 103 subjects captured in three different sessions considering the different real-world scenarios.
no code implementations • 3 May 2021 • Priyanka Sinha, Pabitra Mitra, Antonio Anastasio Bruto da Costa, Nikolaos Kekatos
Multi-party dialogues are common in enterprise social media on technical as well as non-technical topics.
no code implementations • 8 Sep 2020 • Tianjian Huang, Prajwal Singhania, Maziar Sanjabi, Pabitra Mitra, Meisam Razaviyayn
For such optimization problems, we study the performance of the Alternating Direction Method of Multipliers for Quantization ($\texttt{ADMM-Q}$) algorithm, which is a variant of the widely-used ADMM method applied to our discrete optimization problem.
no code implementations • 20 Feb 2020 • Manashi Chakraborty, Mayukh Roy, Prabir Kumar Biswas, Pabitra Mitra
In this paper, we present a texture aware lightweight deep learning framework for iris recognition.
no code implementations • 27 Jun 2019 • Anirban Santara, Rishabh Madan, Balaraman Ravindran, Pabitra Mitra
Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment.
1 code implementation • Submitted to ACMMM-2019 2019 • Anirban Santara, Jayeeta Datta, Sourav Sarkar, Ankur Garg, Kirti Padia, Pabitra Mitra
In order to address these issues, we aim to develop a framework for material-agnostic information retrieval in hyperspectral images based on Positive-Unlabelled (PU) classification.
no code implementations • 21 Jan 2019 • Debarghya China, Pabitra Mitra, Debdoot Sheet
Coronary artery disease accounts for a large number of deaths across the world and clinicians generally prefer using x-ray computed tomography or magnetic resonance imaging for localizing vascular pathologies.
1 code implementation • 21 Jan 2019 • Sumanth Nandamuri, Debarghya China, Pabitra Mitra, Debdoot Sheet
Ultrasound imaging is generally employed for real-time investigation of internal anatomy of the human body for disease identification.
no code implementations • 17 Jan 2019 • Debarghya China, Francis Tom, Sumanth Nandamuri, Aupendu Kar, Mukundhan Srinivasan, Pabitra Mitra, Debdoot Sheet
Ultrasound image compression by preserving speckle-based key information is a challenging task.
no code implementations • 5 Dec 2018 • Sourav Pal, Tharun Mohandoss, Pabitra Mitra
The first method is a supervised learning approach in which we collect eye-gaze data for the task of driving and use this to train a model for predicting the attention map.
no code implementations • WS 2018 • Malay Pramanick, Pabitra Mitra
Metaphor is a popular figure of speech.
no code implementations • WS 2018 • Malay Pramanick, Ashim Gupta, Pabitra Mitra
In this paper, we propose a method for detection of metaphors at the token level using a hybrid model of Bidirectional-LSTM and CRF.
1 code implementation • 16 Nov 2017 • Avisek Lahiri, Arnav Jain, Prabir Kumar Biswas, Pabitra Mitra
Contemporary benchmark methods for image inpainting are based on deep generative models and specifically leverage adversarial loss for yielding realistic reconstructions.
no code implementations • WS 2017 • Jeenu Grover, Pabitra Mitra
In this paper, we propose a novel two step algorithm for sentence alignment in monolingual corpora using Unfolding Recursive Autoencoders.
1 code implementation • 1 Dec 2016 • Anirban Santara, Kaustubh Mani, Pranoot Hatwar, Ankit Singh, Ankur Garg, Kirti Padia, Pabitra Mitra
Deep learning based landcover classification algorithms have recently been proposed in literature.
Ranked #12 on Hyperspectral Image Classification on Indian Pines (Overall Accuracy metric)
no code implementations • 20 Nov 2016 • Arnav Kumar Jain, Abhinav Agarwalla, Kumar Krishna Agrawal, Pabitra Mitra
In this paper, we introduce Key-Value Memory Networks to a multimodal setting and a novel key-addressing mechanism to deal with sequence-to-sequence models.
no code implementations • 3 May 2016 • Avisek Lahiri, Sourya Roy, Anirban Santara, Pabitra Mitra, Prabir Kumar Biswas
Recent thrust in saliency prediction research is to learn high level semantics using ground truth eye fixation datasets.
no code implementations • 17 Apr 2016 • Sourya Roy, Pabitra Mitra
In this paper we propose a Kalman filter aided saliency detection model which is based on the conjecture that salient regions are considerably different from our "visual expectation" or they are "visually surprising" in nature.
2 code implementations • 10 Apr 2016 • Biswajit Paria, Vikas Reddy, Anirban Santara, Pabitra Mitra
The success of deep neural networks is mostly due their ability to learn meaningful features from the data.
1 code implementation • 15 Mar 2016 • Debapriya Maji, Anirban Santara, Pabitra Mitra, Debdoot Sheet
In this work we present a computational imaging framework using deep and ensemble learning for reliable detection of blood vessels in fundus color images.
no code implementations • 9 Mar 2016 • Anirban Santara, Debapriya Maji, DP Tejas, Pabitra Mitra, Arobinda Gupta
In this paper a synchronized parallel algorithm for pre-training deep networks on multi-core machines has been proposed.
1 code implementation • 20 Nov 2015 • Souradeep Chakraborty, Pabitra Mitra
We present an algorithm for graph based saliency computation that utilizes the underlying dense subgraphs in finding visually salient regions in an image.
no code implementations • 7 Jul 2013 • Arindam Chaudhuri, Kajal De, Dipak Chatterjee, Pabitra Mitra
The multivalued nature of Fuzzy Sets allows handling of uncertainty and vagueness involved in the cost values of each cells in the transportation table.