1 code implementation • 2 Jul 2023 • Furkan Gursoy, Ioannis A. Kakadiaris
Generalizing this intuition, this paper proposes a new equal confusion fairness test to check an automated decision system for fairness and a new confusion parity error to quantify the extent of any unfairness.
no code implementations • 14 Sep 2022 • Eric Ingram, Furkan Gursoy, Ioannis A. Kakadiaris
Criminal recidivism models are tools that have gained widespread adoption by parole boards across the United States to assist with parole decisions.
no code implementations • 16 Aug 2022 • Furkan Gursoy, Ioannis A. Kakadiaris
Overall, the proposed regression fairness testing methodology fills a gap in the fair machine learning literature and may serve as a part of larger accountability assessments and algorithm audits.
no code implementations • 1 Mar 2022 • Furkan Gursoy, Ioannis A. Kakadiaris
This work also proposes system cards to serve as scorecards presenting the outcomes of such audits.
no code implementations • 26 Jan 2021 • Mahsa Shafaei, Christos Smailis, Ioannis A. Kakadiaris, Thamar Solorio
In this work, we explore different approaches to combine modalities for the problem of automated age-suitability rating of movie trailers.
no code implementations • 8 Oct 2020 • Ha Le, Ioannis A. Kakadiaris
In this paper, we introduce Domain-Based Label Face (DBLFace), a learning approach based on the assumption that a subject is not represented by a single label but by a set of labels.
no code implementations • 13 Jul 2020 • Ali Memariani, Ioannis A. Kakadiaris
However, detecting C. diff cells in SEM images is a challenging problem due to the presence of inhomogeneous illumination and occlusion.
no code implementations • 11 Jun 2020 • Xiang Xu, Nikolaos Sarafianos, Ioannis A. Kakadiaris
In this paper, we address a key limitation of existing 2D face recognition methods: robustness to occlusions.
no code implementations • ICCV 2019 • Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem.
no code implementations • 12 Mar 2019 • Yuhang Wu, Ioannis A. Kakadiaris
The compact face representation is not sensitive to the number of patches that are used to construct the facial template and is more suitable for incorporating the information from different view angles for image-set based face recognition.
no code implementations • 27 Jan 2019 • Xiang Xu, Ioannis A. Kakadiaris
Biometrics-related research has been accelerated significantly by deep learning technology.
2 code implementations • ECCV 2018 • Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris
For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem.
no code implementations • 15 May 2018 • Lingfeng Zhang, Ioannis A. Kakadiaris
A Fully Associative Patch-based Signature Matcher (FAPSM) is proposed so that the local matching identity of each patch contributes to the global matching identities of all the patches.
no code implementations • 7 May 2018 • Lingfeng Zhang, Ioannis A. Kakadiaris
This paper focuses on improving the performance of current convolutional neural networks in visual recognition without changing the network architecture.
no code implementations • 3 Apr 2018 • Lingfeng Zhang, Pengfei Dou, Ioannis A. Kakadiaris
Three ways are introduced to learn the global matching: majority voting, l1-regularized weighting, and decision rule.
no code implementations • 25 Mar 2018 • Lingfeng Zhang, Pengfei Dou, Ioannis A. Kakadiaris
This paper focuses on improving face recognition performance with a new signature combining implicit facial features with explicit soft facial attributes.
no code implementations • 17 Mar 2018 • Yuhang Wu, Le Anh Vu Ha, Xiang Xu, Ioannis A. Kakadiaris
The method relies on Convolutional Point-set Representation (CPR), a carefully designed matrix representation to summarize different layers of information encoded in the set of detected points in the annotated image.
no code implementations • 19 Sep 2017 • Michalis Vrigkas, Evangelos Kazakos, Christophoros Nikou, Ioannis A. Kakadiaris
In this work, a novel method based on the learning using privileged information (LUPI) paradigm for recognizing complex human activities is proposed that handles missing information during testing.
no code implementations • 19 Sep 2017 • Xiang Xu, Pengfei Dou, Ha A. Le, Ioannis A. Kakadiaris
Extensive experiments are conducted on the UHDB31 and IJB-A, demonstrating that UR2D outperforms existing 2D face recognition systems such as VGG-Face, FaceNet, and a commercial off-the-shelf software (COTS) by at least 9% on the UHDB31 dataset and 3% on the IJB-A dataset on average in face identification tasks.
no code implementations • 19 Sep 2017 • Nikolaos Sarafianos, Theodore Giannakopoulos, Christophoros Nikou, Ioannis A. Kakadiaris
In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework.
no code implementations • 2 Sep 2017 • Yuhang Wu, Ioannis A. Kakadiaris
The visual clues extracted from the fiducial points, non-fiducial points, and facial contour are jointly employed to verify the hypotheses.
no code implementations • 31 Aug 2017 • Michalis Vrigkas, Evangelos Kazakos, Christophoros Nikou, Ioannis A. Kakadiaris
Classification models may often suffer from "structure imbalance" between training and testing data that may occur due to the deficient data collection process.
no code implementations • 30 Aug 2017 • Nikolaos Sarafianos, Michalis Vrigkas, Ioannis A. Kakadiaris
Incorporating additional knowledge in the learning process can be beneficial for several computer vision and machine learning tasks.
no code implementations • 29 Aug 2017 • Nikolaos Sarafianos, Theodore Giannakopoulos, Christophoros Nikou, Ioannis A. Kakadiaris
Visual attributes, from simple objects (e. g., backpacks, hats) to soft-biometrics (e. g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification.
no code implementations • CVPR 2017 • Pengfei Dou, Shishir K. Shah, Ioannis A. Kakadiaris
Inspired by the success of deep neural networks (DNN), we propose a DNN-based approach for End-to-End 3D FAce Reconstruction (UH-E2FAR) from a single 2D image.
no code implementations • 7 Apr 2017 • Yuhang Wu, Shishir K. Shah, Ioannis A. Kakadiaris
Facial landmark localization is a fundamental module for pose-invariant face recognition.
no code implementations • 9 Feb 2017 • Nikolaos Sarafianos, Christophoros Nikou, Ioannis A. Kakadiaris
In this paper, we propose a novel regression-based method for employing privileged information to estimate the height using human metrology.
no code implementations • CVPR 2013 • Yen H. Le, Uday Kurkure, Ioannis A. Kakadiaris
For each model point, an ensemble of regressors is built.