@Article{Moreira2022,
author={Moreira, Daniel
and Cardenuto, Jo{\~a}o Phillipe
and Shao, Ruiting
and Baireddy, Sriram
and Cozzolino, Davide
and Gragnaniello, Diego
and Abd-Almageed, Wael
and Bestagini, Paolo
and Tubaro, Stefano
and Rocha, Anderson
and Scheirer, Walter
and Verdoliva, Luisa
and Delp, Edward},
title={SILA: a system for scientific image analysis},
journal={Scientific Reports},
year={2022},
month={Oct},
day={31},
volume={12},
number={1},
pages={18306},
 	keywords="journal", 

abstract={A great deal of the images found in scientific publications are retouched, reused, or composed to enhance the quality of the presentation. In most instances, these edits are benign and help the reader better understand the material in a paper. However, some edits are instances of scientific misconduct and undermine the integrity of the presented research. Determining the legitimacy of edits made to scientific images is an open problem that no current technology can perform satisfactorily in a fully automated fashion. It thus remains up to human experts to inspect images as part of the peer-review process. Nonetheless, image analysis technologies promise to become helpful to experts to perform such an essential yet arduous task. Therefore, we introduce SILA, a system that makes image analysis tools available to reviewers and editors in a principled way. Further, SILA is the first human-in-the-loop end-to-end system that starts by processing article PDF files, performs image manipulation detection on the automatically extracted figures, and ends with image provenance graphs expressing the relationships between the images in question, to explain potential problems. To assess its efficacy, we introduce a dataset of scientific papers from around the globe containing annotated image manipulations and inadvertent reuse, which can serve as a benchmark for the problem at hand. Qualitative and quantitative results of the system are described using this dataset.},
issn={2045-2322},
doi={10.1038/s41598-022-21535-3},
url={https://doi.org/10.1038/s41598-022-21535-3}
}

A great deal of the images found in scientific publications are retouched, reused, or composed to enhance the quality of the presentation. In most instances, these edits are benign and help the reader better understand the material in a paper. However, some edits are instances of scientific misconduct and undermine the integrity of the presented research. Determining the legitimacy of edits made to scientific images is an open problem that no current technology can perform satisfactorily in a fully automated fashion. It thus remains up to human experts to inspect images as part of the peer-review process. Nonetheless, image analysis technologies promise to become helpful to experts to perform such an essential yet arduous task. Therefore, we introduce SILA, a system that makes image analysis tools available to reviewers and editors in a principled way. Further, SILA is the first human-in-the-loop end-to-end system that starts by processing article PDF files, performs image manipulation detection on the automatically extracted figures, and ends with image provenance graphs expressing the relationships between the images in question, to explain potential problems. To assess its efficacy, we introduce a dataset of scientific papers from around the globe containing annotated image manipulations and inadvertent reuse, which can serve as a benchmark for the problem at hand. Qualitative and quantitative results of the system are described using this dataset.

@article{Zhu-SW-VAE,
	title = {{SW-VAE}: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping},
	url = {https://arxiv.org/abs/2209.10623},
	journal = {European Conference on Computer Vision Workshop on Learning from Limited and Imperfect Data},
	author = {J. Zhu and H. Xie and W. AbdAlmageed},
	year = {2022}, 
 	keywords="conference"
}

@article{Zhu-Weekly,
	title = {Weakly Supervised Invariant Representation Learning Via Disentangling Known and Unknown Nuisance Factor},
	url = {https://arxiv.org/abs/2209.06827},
	journal = {European Conference on Computer Vision Workshop on VISION WITH BIASED OR SCARCE DATA},
	author = {J. Zhu and H. Xie and W. AbdAlmageed},
	year = {2022}, 
 	keywords="conference"
}

@article{Li-CAT,
	title = {{CAT}: Controllable Attribute Translation for Fair Facial Attribute Classification},
	url = {https://arxiv.org/abs/2209.06850},
	journal = {European Conference on Computer Vision Workshop on VISION WITH BIASED OR SCARCE DATA},
	author = {J. Li and W. AbdAlmageed},
	year = {2022}, 
 	keywords="conference"
}

@article{Sabir-MONET,
	title = {{MONet}: Multi-scale Overlap Network for Duplication Detection in Biomedical Images},
	url = {https://arxiv.org/abs/2207.09107?context=cs},
	journal = {IEEE International Conference on Image Processing},
	author = {E. Sabir and S. Nandi and W. AbdAlmageed and P. Natarajan},
	year = {2022}, 
 	keywords="conference"
}

@article{Song-Learning,
	title = {Learning Robust Representations Of Generative Models Using Set-Based Artificial Fingerprints},
	url = {https://arxiv.org/pdf/2206.02067.pdf},
	author = {H. Song and W. AbdAlmageed},
	year = {2022}, 
 	keywords="arxiv"
}

@article{Do-op-Zhu,
	title = {{Do-Operation} Guided Causal Representation Learning with Reduced Supervision Strength},
	url = {https://arxiv.org/pdf/2206.01802},
	journal = {NeurIPS workshop on  Causal Machine Learning for Real-World Impact},
	author = {J. Zhu and H. Xie and W. AbdAlmageed},
	year = {2022}, 
 	keywords="conference"
}

@article{Cheng-Attack,
	title = {Attack-Agnostic Adversarial Detection},
	url = {https://arxiv.org/pdf/2206.00489},
	journal = {NeurIPS workshop on  Trustworthy and Socially Responsible
Machine Learning},
	author = {J. Cheng and M. Hussein and J. Billa and W. AbdAlmageed},
	year = {2022}, 
 	keywords="conference"
}

@article{Datta,
	title = {{P2M-DeTrack}: Processing-in-Pixel-in-Memory for Energy-efficient and Real-Time Multi-Object Detection and Tracking},
	url = {https://arxiv.org/pdf/2205.14285},
	author = {Gourav Datta and Souvik Kundu and Zihan Yin and Joe Mathai and Zeyu Liu and Zixu Wang and Mulin Tian and Shunlin Lu and Ravi T Lakkireddy and Andrew Schmidt and Wael Abd-Almageed and Ajey P Jacob and Akhilesh R Jaiswal and Peter A Beerel},
	year = {2022}, 
 	keywords="arxiv"
}

@inproceedings{Jiazhi2021,
  title={Information-Theoretic Bias Assessment Of Learned Representations of Pretrained Face Recognition},
  author={Li, Jiazhi and AbdAlmageed, Wael},
  booktitle={2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)},
  year={2021},
  organization={IEEE},
  keywords="conference"
}

@inproceedings{hangameh2021,
  title={Explaining Face Presentation Attack Detection Using Natural Language},
  author={Hengameh Mirzaalian and Mohamed Hussein and  Leonidas Spinoulas and Jonathan May and Wael Abd-Almageed},
  booktitle={2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)},
  year={2021},
  organization={IEEE},
  keywords="conference"
}

@article{cao_icdar_2021,
	title = {Customizable Camera Verification for Media Forensic},
	author = {Huaigu Cao and Wael AbdAlmageed},
	journal = {International Conference on Document Analysis and Recognition},
	year = {2021},
	keywords="conference"
}

@article{rostami_iccv_2021,
	title = {Detection and Continual Learning of Novel Face Presentation Attacks},
	author = {Mohammad Rostami and Leonidas Spinoulas and 
Mohamed Hussein and Wael Abd-Almageed},
	journal = {International Conference on Computer Vision},
	year = {2021},
	keywords="conference"
}

@article{Ma_iccv_2021,
	title = {Partner-Assisted Learning for Few-Shot Image Classification},
	author = {Jiawei Ma and Hanchen Xie and Guangxing Han and Shih-Fu Chang and  Aram Galstyan and Wael Abd-Almageed },
	journal = {International Conference on Computer Vision},
	year = {2021},
	keywords="conference"
}

@article{Cheng_iccv_2021,
	title = {SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation},
	author = {Jiaxin Cheng and Soumyaroop Nandi and Prem Natarajan and Wael Abd-Almageed},
	journal = {International Conference on Computer Vision},
	year = {2021},
	keywords="conference"
}

@article{Sabir_iccv_2021,
	title = {BioFors: A Large Biomedical Image Forensics Dataset},
	author = {Ekraam Sabir and Soumyaroop Nandi and Wael Abd-Almageed and  Prem Natarajan},
	journal = {International Conference on Computer Vision},
	year = {2021},
	keywords="conference"
}





%----------------------------

@article{PES_2021,
	title = {Assessment of Combined Brain-Face Morphology in Youth with Congenital Adrenal Hyperplasia due to 21-Hydroxylase Deficiency},
	volume = {4},
	issn = {2472-1972},
	number = {Supplement\_1},
	journal = {Pediatric Endocrine Society},
	author = {H. Mirzaalian  and M. Hertingand and J.P.  Lewinger and S. Ahmed and N. R. Fraga and L. Randolph and M. E. Geffner and  S.  Kohli and W.  AbdAlmageed and M. S.  Kim},
	year = {2021}, 
	keywords="abstract"
}

@article{xie_muscle_2021,
	title = {{MUSCLE}: {Strengthening} {Semi}-{Supervised} {Learning} {Via} {Concurrent} {Unsupervised} {Learning} {Using} {Mutual} {Information} {Maximization}},
	shorttitle = {{MUSCLE}},
	url = {http://arxiv.org/abs/2012.00150},
	abstract = {Deep neural networks are powerful, massively parameterized machine learning models that have been shown to perform well in supervised learning tasks. However, very large amounts of labeled data are usually needed to train deep neural networks. Several semi-supervised learning approaches have been proposed to train neural networks using smaller amounts of labeled data with a large amount of unlabeled data. The performance of these semi-supervised methods significantly degrades as the size of labeled data decreases. We introduce Mutual-information-based Unsupervised \& Semi-supervised Concurrent LEarning (MUSCLE), a hybrid learning approach that uses mutual information to combine both unsupervised and semi-supervised learning. MUSCLE can be used as a stand-alone training scheme for neural networks, and can also be incorporated into other learning approaches. We show that the proposed hybrid model outperforms state of the art on several standard benchmarks, including CIFAR-10, CIFAR-100, and Mini-Imagenet. Furthermore, the performance gain consistently increases with the reduction in the amount of labeled data, as well as in the presence of bias. We also show that MUSCLE has the potential to boost the classification performance when used in the fine-tuning phase for a model pre-trained only on unlabeled data.},
	
	journal = {IEEE Winter Conference on Applications of Computer Vision},
	author = {Xie, Hanchen and Hussein, Mohamed E. and Galstyan, Aram and AbdAlmageed, Wael},
	month = "Jan.",
	year = {2021},
	file = {arXiv Fulltext PDF:/Users/wamageed/Zotero/storage/W2ZZSQI4/Xie et al. - 2020 - MUSCLE Strengthening Semi-Supervised Learning Via.pdf:application/pdf;arXiv.org Snapshot:/Users/wamageed/Zotero/storage/IZKD4EFW/2012.html:text/html},
	keywords="conference"
}

Deep neural networks are powerful, massively parameterized machine learning models that have been shown to perform well in supervised learning tasks. However, very large amounts of labeled data are usually needed to train deep neural networks. Several semi-supervised learning approaches have been proposed to train neural networks using smaller amounts of labeled data with a large amount of unlabeled data. The performance of these semi-supervised methods significantly degrades as the size of labeled data decreases. We introduce Mutual-information-based Unsupervised & Semi-supervised Concurrent LEarning (MUSCLE), a hybrid learning approach that uses mutual information to combine both unsupervised and semi-supervised learning. MUSCLE can be used as a stand-alone training scheme for neural networks, and can also be incorporated into other learning approaches. We show that the proposed hybrid model outperforms state of the art on several standard benchmarks, including CIFAR-10, CIFAR-100, and Mini-Imagenet. Furthermore, the performance gain consistently increases with the reduction in the amount of labeled data, as well as in the presence of bias. We also show that MUSCLE has the potential to boost the classification performance when used in the fine-tuning phase for a model pre-trained only on unlabeled data.

@article{spinoulas_sensors_2021,
	title = {Multispectral Biometrics System Framework: Application to Presentation Attack Detection},
	journal = {IEEE Sensors },
	year="2021",
	author = {Leonidas Spinoulas and
        Mohamed Hussein and
        David Geissb{\"u}hler and 
        Joe Mathai and Oswin G. Almeida and Guillaume Clivaz and S{\'e}bastien Marcel 
        and Wael AbdAlmageed},
keywords="journal"
}

@article{spinoulas_tbiom_2021,
	title = {Multi-Modal Fingerprint Presentation Attack Detection: Evaluation On A New Dataset},
	journal = {IEEE Transactions on Biometrics},
	year="2021",
	author = {Leonidas Spinoulas and Hengameh Mirzaalian and
        Mohamed Hussein and Wael AbdAlmageed},
keywords="journal"
}

@article{jati2021adversarial,
  title={Adversarial attack and defense strategies for deep speaker recognition systems},
  author={Jati, Arindam and Hsu, Chin-Cheng and Pal, Monisankha and Peri, Raghuveer and AbdAlmageed, Wael and Narayanan, Shrikanth},
  journal={Computer Speech \& Language},
  volume={68},
  pages={101199},
  year={2021},
  publisher={Elsevier}, 
  keywords="journal"
}

@article{pal2020adversarial,
  title={Adversarial defense for deep speaker recognition using hybrid adversarial training},
  author={Pal, Monisankha and Jati, Arindam and Peri, Raghuveer and Hsu, Chin-Cheng and AbdAlmageed, Wael and Narayanan, Shrikanth},
  journal = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2021}, 
  keywords="conference"
}

@inproceedings{jaiswal_unsupervised_2018,
	title = {Unsupervised {Adversarial} {Invariance}},
	booktitle = {Advances in {Neural} {Information} {Processing} {Systems} ({NIPS})},
	author = {Jaiswal, Ayush and Wu, Y. and AbdAlmageed, W. and Natarajan, P.},
	month = dec,
	year = {2018}
}

@inproceedings{wu_busternet:_2018,
	title = {{BusterNet}: {Detecting} {Copy}-{Move} {Image} {Forgery} with {Source}/{Target} {Localization}},
	url = {http://openaccess.thecvf.com/content_ECCV_2018/papers/Rex_Yue_Wu_BusterNet_Detecting_Copy-Move_ECCV_2018_paper.pdf},
	booktitle = {European {Conference} on {Computer} {Vision} ({ECCV})},
	author = {Wu, Y. and AbdAlmageed, W. and Natarajan, P.},
	month = sep,
	year = {2018},
	pages = {168--184}
}

@inproceedings{sabir_deep_2018,
	title = {Deep {Multimodal} {Image}-{Repurposing} {Detection}},
	url = {https://arxiv.org/abs/1808.06686},
	booktitle = {{ACM} {Multimedia} 2018},
	author = {Sabir, E. and AbdAlmageed, W. and Wu, Y. and Natarajan, P.},
	month = oct,
	year = {2018}
}

@inproceedings{wu_image_2018,
	title = {Image {Copy}-{Move} {Forgery} {Detection} via an {End}-to-{End} {Deep} {Neural} {Network}},
	isbn = {978-1-5386-4886-5},
	url = {doi.ieeecomputersociety.org/10.1109/WACV.2018.00211},
	doi = {10.1109/WACV.2018.00211},
	booktitle = {2018 {IEEE} {Winter} {Conference} on {Applications} of {Computer} {Vision} ({WACV})},
	author = {Wu, Y. and AbdAlmageed, W. and Natarajan, P.},
	month = mar,
	year = {2018},
	keywords = {affine transforms, convolution, Feature extraction, feedforward neural nets, image forensics},
	pages = {1907--1915}
}

@inproceedings{jaiswal_bidirectional_2018,
	title = {Bidirectional {Conditional} {Generative} {Adversarial} {Networks}},
	booktitle = {Asian {Conference} on {Computer} {Vision}},
	author = {Jaiswal, A. and Wu, Y. and AbdAlmageed, W. and Natarajan, P.},
	month = dec,
	year = {2018}
}

@inproceedings{li_weighted_2018,
	title = {Weighted {Feature} {Pooling} {Network} in {Template}-{Based} {Recognition}},
	booktitle = {Asian {Conference} on {Computer} {Vision}},
	author = {Li, Z. and Wu, Y. and AbdAlmageed, W. and Natarajan, W.},
	month = dec,
	year = {2018}
}

@inproceedings{cheng_image--gps_2018,
	title = {Image-to-{GPS} {Verification} {Through} {A} {Bottom}-{Up} {Pattern} {Matching} {Network}},
	booktitle = {Asian {Conference} on {Computer} {Vision}},
	author = {Cheng, J. and Wu, Y. and AbdAlmageed, W. and Natarajan, P.},
	month = dec,
	year = {2018}
}

@inproceedings{hussein_fingerprint_2018,
	title = {Fingerprint {Presentation} {Attack} {Detection} {Using} {A} {Novel} {Multi}-{Spectral} {Capture} {Device} and {Patch}-{Based} {Convolutional} {Neural} {Networks}},
	booktitle = {{IEEE} {Workshop} on {Information} {Forensics} and {Security}},
	author = {Hussein, M. and Spinoulas, L. and Xiong, F. and AbdAlmageed, W.},
	month = dec,
	year = {2018}
}

@inproceedings{xiong_unknown_2018,
	title = {Unknown {Presentation} {Attack} {Detection} with {Face} {RGB} {Images}},
	booktitle = {{IEEE} {International} {Conference} on {Biometrics}: {Theory}, {Applications}, and {Systems}},
	author = {Xiong, F. and AbdAlmageed, W.},
	month = oct,
	year = {2018}
}

@article{masi_learning_2018,
	title = {Learning {Pose}-{Aware} {Models} for {Pose}-{Invariant} {Face} {Recognition} in the {Wild}},
	url = {http://ieeexplore.ieee.org/document/8255649/},
	journal = {IEEE Trans. on Pattern Analysis and Machine Intelligence},
	author = {Masi, I. and Chang, F. and Choi, J. and Harel, S. and Kim, J. and Kim, K. and Leksut, J. and Rawls, S. and Wu, Y. and Hassner, Tal and AbdAlmageed, W. and Medioni, G. and Morency, L.P. and Natarajan, P. and Nevatia, R.},
	month = jan,
	year = {2018}
}

@article{jaiswal_capsulegan:_2018,
	title = {{CapsuleGAN}: {Generative} {Adversarial} {Capsule} {Network}},
	shorttitle = {{CapsuleGAN}},
	url = {https://arxiv.org/abs/1802.06167},
	journal = {European Conference on Computer Vision Workshop on Brain-Driven Computer Vision},
	author = {Jaiswal, A. and AbdAlmageed, W. and Natarajan, P.},
	month = sep,
	year = {2018}
}