1 code implementation • 29 Mar 2024 • Jaisidh Singh, Ishaan Shrivastava, Mayank Vatsa, Richa Singh, Aparna Bharati
Using CC-Neg along with modifications to the contrastive loss of CLIP, our proposed CoN-CLIP framework, has an improved understanding of negations.
no code implementations • 16 Feb 2024 • Mahapara Khurshid, Mayank Vatsa, Richa Singh
The rising global prevalence of skin conditions, some of which can escalate to life-threatening stages if not timely diagnosed and treated, presents a significant healthcare challenge.
no code implementations • 7 Dec 2023 • Mayank Vatsa, Anubhooti Jain, Richa Singh
Recently, transformers have become incredibly popular in computer vision and vision-language tasks.
no code implementations • 24 Oct 2023 • Surbhi Mittal, Kartik Thakral, Richa Singh, Mayank Vatsa, Tamar Glaser, Cristian Canton Ferrer, Tal Hassner
However, machine and deep learning algorithms, popular in the AI community today, depend heavily on the data used during their development.
no code implementations • 11 Oct 2023 • Mahapara Khurshid, Mayank Vatsa, Richa Singh
The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network.
no code implementations • the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 • Kartik Narayan, Harsh Agarwal, Kartik Thakral, Surbhi Mittal, Mayank Vatsa, Richa Singh
In this research, we emulate the real-world scenario of deepfake generation and spreading, and propose the DF-Platter dataset, which contains (i) both low-resolution and high-resolution deepfakes generated using multiple generation techniques and (ii) single-subject and multiple-subject deepfakes, with face images of Indian ethnicity.
no code implementations • 7 Nov 2022 • Surbhi Mittal, Kartik Thakral, Puspita Majumdar, Mayank Vatsa, Richa Singh
Since facial region localization is an essential task for all face recognition pipelines, it is imperative to analyze the presence of such bias in popular deep models.
no code implementations • 19 Sep 2022 • Kartik Narayan, Harsh Agarwal, Kartik Thakral, Surbhi Mittal, Mayank Vatsa, Richa Singh
In order to enable the research community to address these questions, this paper proposes DeePhy, a novel Deepfake Phylogeny dataset which consists of 5040 deepfake videos generated using three different generation techniques.
1 code implementation • 27 Aug 2022 • Sasikanth Kotti, Mayank Vatsa, Richa Singh
Datasets for training face verification systems are difficult to obtain and prone to privacy issues.
no code implementations • 13 Dec 2021 • Richa Singh, Puspita Majumdar, Surbhi Mittal, Mayank Vatsa
In this paper, we encapsulate bias detection/estimation and mitigation algorithms for facial analysis.
no code implementations • 6 Oct 2021 • Pavani Tripathi, Yasmeena Akhter, Mahapara Khurshid, Aditya Lakra, Rohit Keshari, Mayank Vatsa, Richa Singh
We present deep learning-based eye segmentation and multitask network classification networks for cataract detection using NIR images as input.
no code implementations • 15 Sep 2021 • Aayushi Agarwal, Akshay Agarwal, Sayan Sinha, Mayank Vatsa, Richa Singh
MD-CSDNetwork is a novel cross-stitched network with two parallel branches carrying the spatial and frequency information, respectively.
1 code implementation • 14 Aug 2021 • Puspita Majumdar, Surbhi Mittal, Richa Singh, Mayank Vatsa
We provide a systematic analysis to evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions across different \textit{gender} and \textit{race} subgroups.
no code implementations • 17 Jun 2021 • Shiksha Mishra, Puspita Majumdar, Richa Singh, Mayank Vatsa
We have also benchmarked the performance of existing face recognition models on the proposed IMFW dataset.
no code implementations • 1 May 2021 • Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh
While fine-grained classification with high resolution images has received significant attention, limited attention has been given to low resolution images.
no code implementations • 25 Apr 2021 • Saheb Chhabra, Puspita Majumdar, Mayank Vatsa, Richa Singh
Projection algorithms learn a transformation function to project the data from input space to the feature space, with the objective of increasing the inter-class distance.
no code implementations • 11 Nov 2020 • Daksha Yadav, Naman Kohli, Mayank Vatsa, Richa Singh, Afzel Noore
In this paper, we propose a novel algorithm for matching faces with temporal variations caused due to age progression.
no code implementations • 2 Nov 2020 • Richa Singh, Mayank Vatsa, Nalini Ratha
Modern AI systems are reaping the advantage of novel learning methods.
no code implementations • 29 Oct 2020 • Divyam Anshumaan, Akshay Agarwal, Mayank Vatsa, Richa Singh
Experiments are performed using multiple databases and CNN models to establish the effectiveness of the proposed WaveTransform attack and analyze the importance of a particular frequency component.
1 code implementation • 25 Oct 2020 • Nilay Sanghvi, Sushant Kumar Singh, Akshay Agarwal, Mayank Vatsa, Richa Singh
The major problem with existing work is the generalizability against multiple attacks both in the seen and unseen setting.
no code implementations • 25 Oct 2020 • Mehak Gupta, Vishal Singh, Akshay Agarwal, Mayank Vatsa, Richa Singh
Presentation attacks are posing major challenges to most of the biometric modalities.
no code implementations • 25 Oct 2020 • Saheb Chhabra, Akshay Agarwal, Richa Singh, Mayank Vatsa
However, the lack of generalizability of existing defense algorithms and the high variability in the performance of the attack algorithms for different databases raises several questions on the effectiveness of the defense algorithms.
no code implementations • 8 Aug 2020 • Rohit Keshari, Soumyadeep Ghosh, Saheb Chhabra, Mayank Vatsa, Richa Singh
However, there are a lot of \textit{small sample size or $S^3$} problems for which it is not feasible to collect large training databases.
no code implementations • 5 Aug 2020 • Puspita Majumdar, Saheb Chhabra, Richa Singh, Mayank Vatsa
Deaths and injuries are common in road accidents, violence, and natural disaster.
no code implementations • 3 Aug 2020 • Aakarsh Malhotra, Surbhi Mittal, Puspita Majumdar, Saheb Chhabra, Kartik Thakral, Mayank Vatsa, Richa Singh, Santanu Chaudhury, Ashwin Pudrod, Anjali Agrawal
Firstly, we present the COVID-19 Multi-Task Network which is an automated end-to-end network for COVID-19 screening.
1 code implementation • IEEE Transactions on Biometrics, Behavior, and Identity Science 2020 • Anshuman Suri, Mayank Vatsa, Richa Singh
Face recognition in the unconstrained environment is an ongoing research challenge.
1 code implementation • CVPR 2020 • Rohit Keshari, Richa Singh, Mayank Vatsa
A well trained and generalized deep neural network (DNN) should be robust to both seen and unseen classes.
no code implementations • 7 Feb 2020 • Richa Singh, Akshay Agarwal, Maneet Singh, Shruti Nagpal, Mayank Vatsa
Face recognition algorithms have demonstrated very high recognition performance, suggesting suitability for real world applications.
1 code implementation • 21 Jan 2020 • Prabhat Kumar, Mayank Vatsa, Richa Singh
This has led to an increase in alterations in images and videos to make them more informative and eye-catching for the viewers worldwide.
no code implementations • 26 Nov 2019 • Raunak Sinha, Anush Sankaran, Mayank Vatsa, Richa Singh
Five different GAN models are implemented as a part of this framework and the performance of the different GAN models are shown using the benchmark MNIST dataset.
1 code implementation • IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS), 2019 2019 • Anshuman Suri, Mayank Vatsa, Richa Singh
Recent advancements in deep learning have significantly increased the capabilities of face recognition.
no code implementations • ICCV 2019 • Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa
The proposed architecture utilizes a combination of capsule and convolutional layers for learning an effective VLR recognition model.
no code implementations • CVPR 2019 • Soumyadeep Ghosh, Richa Singh, Mayank Vatsa
The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class.
no code implementations • 2 Apr 2019 • Shruti Nagpal, Maneet Singh, Richa Singh, Mayank Vatsa
This research attempts to answer these questions and presents an in-depth analysis of `bias' in deep learning based face recognition systems.
no code implementations • 26 Jan 2019 • Anubhav Jain, Richa Singh, Mayank Vatsa
For distinguishing between real images and images generated using GANs, the proposed algorithm yields an accuracy of 99. 83%.
no code implementations • 10 Dec 2018 • Saheb Chhabra, Puspita Majumdar, Mayank Vatsa, Richa Singh
Stimulated by the advances in adversarial perturbations, this research proposes the concept of Data Fine-tuning to improve the classification accuracy of a given model without changing the parameters of the model.
no code implementations • 10 Dec 2018 • Rohit Keshari, Richa Singh, Mayank Vatsa
Dropout is often used in deep neural networks to prevent over-fitting.
no code implementations • 21 Nov 2018 • Maneet Singh, Richa Singh, Mayank Vatsa, Nalini Ratha, Rama Chellappa
While upcoming algorithms continue to achieve improved performance, a majority of the face recognition systems are susceptible to failure under disguise variations, one of the most challenging covariate of face recognition.
no code implementations • 18 Nov 2018 • Saksham Suri, Anush Sankaran, Mayank Vatsa, Richa Singh
In this paper, a novel framework is proposed which transfers fundamental visual features learnt from a generic image dataset to supplement a supervised face recognition model.
no code implementations • 2 Nov 2018 • Rishabh Garg, Yashasvi Baweja, Soumyadeep Ghosh, Mayank Vatsa, Richa Singh, Nalini Ratha
Mobile biometric approaches provide the convenience of secure authentication with an omnipresent technology.
no code implementations • 15 Oct 2018 • Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh, Afzel Noore
In this paper, we propose a novel Supervised COSMOS Autoencoder which utilizes a multi-objective loss function to learn representations that simultaneously encode the (i) "similarity" between the input and reconstructed vectors in terms of their direction, (ii) "distribution" of pixel values of the reconstruction with respect to the input sample, while also incorporating (iii) "discriminability" in the feature learning pipeline.
no code implementations • 14 Aug 2018 • Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa, Afzel Noore
Human skull identification is an arduous task, traditionally requiring the expertise of forensic artists and anthropologists.
no code implementations • 30 May 2018 • Naman Kohli, Daksha Yadav, Mayank Vatsa, Richa Singh, Afzel Noore
In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm regularization Autoencoder (SMNAE).
no code implementations • 27 May 2018 • Naman Kohli, Mayank Vatsa, Richa Singh, Afzel Noore, Angshul Majumdar
Utilizing the information obtained from the human study, a hierarchical Kinship Verification via Representation Learning (KVRL) framework is utilized to learn the representation of different face regions in an unsupervised manner.
no code implementations • 23 May 2018 • Saheb Chhabra, Richa Singh, Mayank Vatsa, Gaurav Gupta
A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age.
no code implementations • 21 May 2018 • Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa
Gender is one of the most common attributes used to describe an individual.
no code implementations • CVPR 2018 • Rohit Keshari, Mayank Vatsa, Richa Singh, Afzel Noore
The architecture provides the flexibility of training with both small and large training databases and yields good accuracies even with small size training data.
no code implementations • 20 Mar 2018 • Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh
Predicting if a person is an adult or a minor has several applications such as inspecting underage driving, preventing purchase of alcohol and tobacco by minors, and granting restricted access.
no code implementations • 20 Mar 2018 • Akshay Sethi, Maneet Singh, Richa Singh, Mayank Vatsa
Facial attributes can provide rich ancillary information which can be utilized for different applications such as targeted marketing, human computer interaction, and law enforcement.
no code implementations • 22 Feb 2018 • Gaurav Goswami, Nalini Ratha, Akshay Agarwal, Richa Singh, Mayank Vatsa
In this paper, we attempt to unravel three aspects related to the robustness of DNNs for face recognition: (i) assessing the impact of deep architectures for face recognition in terms of vulnerabilities to attacks inspired by commonly observed distortions in the real world that are well handled by shallow learning methods along with learning based adversaries; (ii) detecting the singularities by characterizing abnormal filter response behavior in the hidden layers of deep networks; and (iii) making corrections to the processing pipeline to alleviate the problem.
no code implementations • 22 Feb 2018 • Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa, Angshul Majumdar
The proposed algorithm learns multi-level sparse representation for both high and low resolution gallery images, along with an identity aware dictionary and a transformation function between the two representations for face identification scenarios.
no code implementations • 30 Jan 2018 • Aditya Lakra, Pavani Tripathi, Rohit Keshari, Mayank Vatsa, Richa Singh
This paper presents an efficient iris segmentation algorithm with variations due to cataract and post cataract surgery.
no code implementations • 29 Oct 2017 • Naman Kohli, Daksha Yadav, Mayank Vatsa, Richa Singh, Afzel Noore
We demonstrate the effect of these synthetically generated iris images as presentation attack on iris recognition by using a commercial system.
no code implementations • ICCV 2017 • Shruti Nagpal, Maneet Singh, Richa Singh, Mayank Vatsa, Afzel Noore, Angshul Majumdar
The performance of the proposed models is evaluated on a novel application of sketch-to-sketch matching, along with sketch-to-digital photo matching.
no code implementations • 8 Oct 2017 • Shruti Nagpal, Maneet Singh, Arushi Jain, Richa Singh, Mayank Vatsa, Afzel Noore
Forensic application of automatically matching skull with face images is an important research area linking biometrics with practical applications in forensics.
no code implementations • 8 Oct 2017 • Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh, Afzel Noore, Angshul Majumdar
Soft biometric modalities have shown their utility in different applications including reducing the search space significantly.
no code implementations • 22 Sep 2017 • Aparna Bharati, Mayank Vatsa, Richa Singh, Kevin W. Bowyer, Xin Tong
However, previous work on this topic has not considered whether or how accuracy of retouching detection varies with the demography of face images.
no code implementations • 31 Jan 2016 • Snigdha Tariyal, Angshul Majumdar, Richa Singh, Mayank Vatsa
In this work we propose a new deep learning tool called deep dictionary learning.