Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleSeptember 2023
Trustworthy Medical Image Segmentation with improved performance for in-distribution samples
Neural Networks (NENE), Volume 166, Issue CPages 127–136https://doi.org/10.1016/j.neunet.2023.06.047AbstractDespite the enormous achievements of Deep Learning (DL) based models, their non-transparent nature led to restricted applicability and distrusted predictions. Such predictions emerge from erroneous In-Distribution (ID) and Out-Of-Distribution (...
- research-articleJune 2023
Exploring the feasibility of adversarial attacks on medical image segmentation
Multimedia Tools and Applications (MTAA), Volume 83, Issue 4Pages 11745–11768https://doi.org/10.1007/s11042-023-15575-8AbstractRecent advancements in Deep Learning (DL) based medical image segmentation models have led to tremendous growth in healthcare applications. However, DL models can be easily compromised by intelligently engineered adversarial attacks, which pose a ...
- research-articleMay 2023
SUNRISE: Improving 3D Mask Face Anti-Spoofing for Short Videos Using Pre-Emptive Split and Merge
IEEE Transactions on Dependable and Secure Computing (TDSC), Volume 20, Issue 3Pages 1927–1940https://doi.org/10.1109/TDSC.2022.3168345In the current digital world, face analytic systems become an integral part of daily life. However, today's cutting-edge technology and readily available social media information make these systems vulnerable through face spoofing attacks. These ...
- research-articleApril 2023
<italic>MERASTC</italic>: Micro-Expression Recognition Using Effective Feature Encodings and 2D Convolutional Neural Network
IEEE Transactions on Affective Computing (ITAC), Volume 14, Issue 2Pages 1431–1441https://doi.org/10.1109/TAFFC.2021.3061967Facial micro-expression (ME) can disclose genuine and concealed human feelings. It makes MEs extensively useful in real-world applications pertaining to affective computing and psychology. Unfortunately, they are induced by subtle facial movements for a ...
- research-articleJuly 2022
D-NEXUS: Defending text networks using summarization
Electronic Commerce Research and Applications (ECRA), Volume 54, Issue Chttps://doi.org/10.1016/j.elerap.2022.101171Highlights- We propose a novel summarization based defence, D-NEXUS, against attacks on the sentiment analysis models.
Sentiment analysis is an important tool for understanding consumer sentiment in e-commerce platforms. Usually, it is performed using Deep Neural Networks (DNNs), owing to their strong predictive and generalization capabilities. ...
-
- research-articleJune 2022
FATALRead - Fooling visual speech recognition models: Put words on Lips
Applied Intelligence (KLU-APIN), Volume 52, Issue 8Pages 9001–9016https://doi.org/10.1007/s10489-021-02846-wAbstractVisual speech recognition is essential in understanding speech in several real-world applications such as surveillance systems and aiding differently-abled. It proliferates the research in the realm of visual speech recognition, also known as ...
- research-articleMay 2022
PERSIST: Improving micro-expression spotting using better feature encodings and multi-scale Gaussian TCN
Applied Intelligence (KLU-APIN), Volume 53, Issue 2Pages 2235–2249https://doi.org/10.1007/s10489-022-03553-wAbstractMicro-expression (ME) is required in real-world applications for understanding true human feeling. The preliminary step of ME analysis, ME spotting, is highly challenging for human experts because MEs induce subtle facial movements for a short ...
- research-articleDecember 2021
Contextual Emotion Learning Challenge
- Jainendra Shukla,
- Puneet Gupta,
- Aniket Bera,
- Arka Sarkar,
- Prakhar Goel,
- Shubhangi Butta,
- Anup Kumar Gupta,
- Snehil Sanyal,
- Debanga Rai Neog,
- M K Bhuyan,
- Kalyani Marathe,
- Linda Shapiro,
- Alex Colbrn,
- Varchita Lalwani
2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)Pages 1–7https://doi.org/10.1109/FG52635.2021.9667034Emotion recognition via vision has been deeply associated with facial expressions, and the inference of emotions has, more often than not, been based on the same. However, context, both environmental and social, plays an imperative role in emotion ...
- research-articleNovember 2021
DARE: Deceiving Audio–Visual speech Recognition model
AbstractAudio–Visual speech recognition (AVSR) is an effective way to predict text corresponding to the spoken words using both audio and face videos, even in a noisy environment. These models find extensive applications in various fields like ...
Highlights- We initiate a targeted attack on AVSR model and detection network simultaneously.
- research-articleNovember 2021
An Encoder-decoder based approach for generating Faces using Facial Attributes using CNN
IC3-2021: Proceedings of the 2021 Thirteenth International Conference on Contemporary ComputingPages 296–302https://doi.org/10.1145/3474124.3474166This paper addresses the challenge of generating faces using facial attributes. Although there are researches the address the problem of generating faces, they do so by using a facial image as a base and changing the required attributes. To solve this ...
- doctoral_thesisJanuary 2020
FPGA Overlay Processor for Deep Neural Networks
AbstractThe rapid advancement of Artificial intelligence (AI) is making our everyday life easier with smart assistants, automatic medical analyzer, bank plagiarism checkers and traffic predictions, etc. Deep learning algorithms, especially deep ...
- research-articleOctober 2019
Goodbye, motherboard. Bare chiplets bonded to silicon will make computers smaller and more powerful: Hello, silicon-interconnect fabric
THE NEED TO MAKE some hardware systems tinier and tinier and others bigger and bigger has been driving innovations in electronics for a long time. The former can be seen in the progression from laptops to smartphones to smart watches to hearables and ...
- ArticleSeptember 2019
MLAttack: Fooling Semantic Segmentation Networks by Multi-layer Attacks
AbstractDespite the immense success of deep neural networks, their applicability is limited because they can be fooled by adversarial examples, which are generated by adding visually imperceptible and structured perturbations to the original image. ...
- ArticleJuly 2018
A Framework for Pervasive and Ubiquitous Geriatric Monitoring
- research-articleNovember 2017
An efficient slap image matching system based on dynamic classifier selection and aggregation
Information Sciences: an International Journal (ISCI), Volume 417, Issue CPages 113–127https://doi.org/10.1016/j.ins.2017.06.043The performance of any existing slap fingerprint image based matching systems is limited because it uses a fixed classifier, a fixed fusion rule and considers all fingerprints in the slap image without giving any importance on the quality of the images. ...
- research-articleSeptember 2017
Accurate heart-rate estimation from face videos using quality-based fusion
2017 IEEE International Conference on Image Processing (ICIP)Pages 4132–4136https://doi.org/10.1109/ICIP.2017.8297060Estimating heart rate (HR) accurately using face videos acquired from a low cost camera in contactless manner is of paramount importance for many real-world applications. Such existing systems perform spuriously due to change in camera parameters, ...
- research-articleJuly 2016
An accurate infrared hand geometry and vein pattern based authentication system
Knowledge-Based Systems (KNBS), Volume 103, Issue CPages 143–155https://doi.org/10.1016/j.knosys.2016.04.008An acquisition system is designed to simultaneously acquire palm dorsal vein and infrared (IR) hand geometry.A novel quality parameter is proposed for palm dorsal vein.A quality based variational approach is proposed for vein extraction that can handle ...
- research-articleJanuary 2016
Hardware Reliability margining for the dark silicon era
2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)Pages 637–642https://doi.org/10.1109/ASPDAC.2016.7428083Hardware reliability margin should be derived from the worst-case aging scenario, which typically occurs when the circuits are operating at peak performance state with the highest operating voltage and frequency. However, as integrated circuits enter the “...
- research-articleApril 2015
A robust singular point detection algorithm
Applied Soft Computing (APSC), Volume 29, Issue CPages 411–423https://doi.org/10.1016/j.asoc.2015.01.027Graphical abstractDisplay Omitted HighlightsThe proposed algorithm can be used to detect singular points, viz. core and delta points, of fingerprints accurately, even if the images are of bad quality.It can be used to classify a fingerprint into one of ...
- research-articleMarch 2015
An accurate finger vein based verification system
Digital Signal Processing (DISP), Volume 38, Issue CPages 43–52https://doi.org/10.1016/j.dsp.2014.12.003This paper makes use of finger vein to propose an accurate personal authentication system. A matched filtering at various scales is applied on the vein image to reduce the effects of noise occurred due to non-uniform illumination, low local contrast, ...