435 citations · 529 across the 13 of their papers we have counts for
15 papers
Low Rank Properties for Estimating Microphones Start Time and Sources Emission Time
Faxian Cao, Yongqiang Cheng, Adil Mehmood Khan +2
Uncertainty in timing information pertaining to the start time of microphone recordings and sources' emission time pose significant challenges in various applications, such as join…
Justices for Information Bottleneck Theory
Faxian Cao, Yongqiang Cheng, Adil Mehmood Khan +1
This study comes as a timely response to mounting criticism of the information bottleneck (IB) theory, injecting fresh perspectives to rectify misconceptions and reaffirm its valid…
Are Microphone Signals Alone Sufficient for Self-Positioning?
Faxian Cao, Yongqiang Cheng, Adil Mehmood Khan +1
In an era where asynchronous environments pose challenges to traditional self-positioning methods, we propose a new transformation to the existing paradigm. Traditionally, time of…
RepFair-GAN: Mitigating Representation Bias in GANs Using Gradient Clipping
Patrik Joslin Kenfack, Kamil Sabbagh, Adín Ramírez Rivera +1
Fairness has become an essential problem in many domains of Machine Learning (ML), such as classification, natural language processing, and Generative Adversarial Networks (GANs).…
Bridging the Domain Gap for Stance Detection for the Zulu language
Gcinizwe Dlamini, Imad Eddine Ibrahim Bekkouch, Adil Khan +1
Misinformation has become a major concern in recent last years given its spread across our information sources. In the past years, many NLP tasks have been introduced in this area,…
Attention Mechanism Meets with Hybrid Dense Network for Hyperspectral Image Classification
Muhammad Ahmad, Adil Mehmood Khan, Manuel Mazzara +3
Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, th…
What augmentations are sensitive to hyper-parameters and why?
Ch Muhammad Awais, Imad Eddine Ibrahim Bekkouch
We apply augmentations to our dataset to enhance the quality of our predictions and make our final models more resilient to noisy data and domain drifts. Yet the question remains,…
Hierarchical Transformer for Multilingual Machine Translation
Albina Khusainova, Adil Khan, Adín Ramírez Rivera +1
The choice of parameter sharing strategy in multilingual machine translation models determines how optimally parameter space is used and hence, directly influences ultimate transla…
On the Fairness of Generative Adversarial Networks (GANs)
Patrik Joslin Kenfack, Daniil Dmitrievich Arapov, Rasheed Hussain +2
Generative adversarial networks (GANs) are one of the greatest advances in AI in recent years. With their ability to directly learn the probability distribution of data, and then s…
Hyperspectral Image Classification: Artifacts of Dimension Reduction on Hybrid CNN
Muhammad Ahmad, Sidrah Shabbir, Rana Aamir Raza +3
Convolutional Neural Networks (CNN) has been extensively studied for Hyperspectral Image Classification (HSIC) more specifically, 2D and 3D CNN models have proved highly efficient…
Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
Muhammad Ahmad, Sidrah Shabbir, Swalpa Kumar Roy +7
Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably…
Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation
Adín Ramírez Rivera, Adil Khan, Imad E. I. Bekkouch +1
Anomaly detection suffers from unbalanced data since anomalies are quite rare. Synthetically generated anomalies are a solution to such ill or not fully defined data. However, synt…
Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks
Konstantin Sozykin, Stanislav Protasov, Adil Khan +2
Automatic analysis of the video is one of most complex problems in the fields of computer vision and machine learning. A significant part of this research deals with (human) activi…
Seeking Optimum System Settings for Physical Activity Recognition on Smartwatches
Muhammad Ahmad, Adil Mehmood Khan, Manuel Mazzara +1
Physical activity recognition (PAR) using wearable devices can provide valued information regarding an individual's degree of functional ability and lifestyle. In this regards, sma…
Segmented and Non-Segmented Stacked Denoising Autoencoder for Hyperspectral Band Reduction
Muhammad Ahmad, Asad Khan, Adil Mehmood Khan +1
Hyperspectral image analysis often requires selecting the most informative bands instead of processing the whole data without losing the key information. Existing band reduction (B…