Search Results for author: Ghassan AlRegib

Found 69 papers, 33 papers with code

A novel attention model for salient structure detection in seismic volumes

no code implementations17 Jan 2022 Muhammad Amir Shafiq, Zhiling Long, Haibin Di, Ghassan AlRegib

Subsequently, a novel directional center-surround attention model is proposed to incorporate directional comparisons around each voxel for saliency detection within each projected dimension.

Saliency Detection Seismic Interpretation

Action Segmentation with Mixed Temporal Domain Adaptation

no code implementations15 Apr 2021 Min-Hung Chen, Baopu Li, Yingze Bao, Ghassan AlRegib

The main progress for action segmentation comes from densely-annotated data for fully-supervised learning.

Action Segmentation Domain Adaptation

Extracting Causal Visual Features for Limited label Classification

no code implementations23 Mar 2021 Mohit Prabhushankar, Ghassan AlRegib

Neural networks trained to classify images do so by identifying features that allow them to distinguish between classes.

General Classification

Contrastive Reasoning in Neural Networks

no code implementations23 Mar 2021 Mohit Prabhushankar, Ghassan AlRegib

In this paper, we formalize the structure of contrastive reasoning and propose a methodology to extract a neural network's notion of contrast.

Object Recognition

Self-Supervised Annotation of Seismic Images using Latent Space Factorization

1 code implementation10 Sep 2020 Oluwaseun Joseph Aribido, Ghassan AlRegib, Mohamed Deriche

Annotating seismic data is expensive, laborious and subjective due to the number of years required for seismic interpreters to attain proficiency in interpretation.

On the Structures of Representation for the Robustness of Semantic Segmentation to Input Corruption

1 code implementation2 Sep 2020 Charles Lehman, Dogancan Temel, Ghassan AlRegib

Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential.

Scene Understanding Semantic Segmentation

Robustness and Overfitting Behavior of Implicit Background Models

1 code implementation21 Aug 2020 Shirley Liu, Charles Lehman, Ghassan AlRegib

In this paper, we examine the overfitting behavior of image classification models modified with Implicit Background Estimation (SCrIBE), which transforms them into weakly supervised segmentation models that provide spatial domain visualizations without affecting performance.

Image Classification Weakly supervised segmentation

Gradients as a Measure of Uncertainty in Neural Networks

no code implementations18 Aug 2020 Jinsol Lee, Ghassan AlRegib

We demonstrate the effectiveness of gradients as a measure of model uncertainty in applications of detecting unfamiliar inputs, including out-of-distribution and corrupted samples.

Out-of-Distribution Detection

Novelty Detection Through Model-Based Characterization of Neural Networks

no code implementations13 Aug 2020 Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

To articulate the significance of the model perspective in novelty detection, we utilize backpropagated gradients.

Implicit Saliency in Deep Neural Networks

no code implementations4 Aug 2020 Yutong Sun, Mohit Prabhushankar, Ghassan AlRegib

In this paper, we show that existing recognition and localization deep architectures, that have not been exposed to eye tracking data or any saliency datasets, are capable of predicting the human visual saliency.

Saliency Detection

Contrastive Explanations in Neural Networks

no code implementations1 Aug 2020 Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib

Current modes of visual explanations answer questions of the form $`Why \text{ } P?'$.

Image Quality Assessment

Spatiotemporal Modeling of Seismic Images for Acoustic Impedance Estimation

no code implementations28 Jun 2020 Ahmad Mustafa, Motaz Alfarraj, Ghassan AlRegib

We empirically compare our proposed workflow with some other sequence modeling-based neural networks that model seismic data only temporally.

Fabric Surface Characterization: Assessment of Deep Learning-based Texture Representations Using a Challenging Dataset

no code implementations16 Mar 2020 Yuting Hu, Zhiling Long, Anirudha Sundaresan, Motaz Alfarraj, Ghassan AlRegib, Sungmee Park, Sundaresan Jayaraman

We formulate the problem as a very fine-grained texture classification problem, and study how deep learning-based texture representation techniques can help tackle the task.

Material Recognition Object Recognition +2

Texture Classification using Block Intensity and Gradient Difference (BIGD) Descriptor

no code implementations4 Feb 2020 Yuting Hu, Zhen Wang, Ghassan AlRegib

In this paper, we present an efficient and distinctive local descriptor, namely block intensity and gradient difference (BIGD).

General Classification Texture Classification

Characterizing Missing Information in Deep Networks Using Backpropagated Gradients

no code implementations ICLR 2020 Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

To complement the learned information from activation-based representation, we propose utilizing a gradient-based representation that explicitly focuses on missing information.

Anomaly Detection

Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics

2 code implementations29 Aug 2019 Dogancan Temel, Min-Hung Chen, Ghassan AlRegib

We investigate the effect of challenging conditions through spectral analysis and show that challenging conditions can lead to distinct magnitude spectrum characteristics.

Traffic Sign Detection Traffic Sign Recognition

Distorted Representation Space Characterization Through Backpropagated Gradients

2 code implementations27 Aug 2019 Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms.

General Classification Image Quality Assessment

Relative Afferent Pupillary Defect Screening through Transfer Learning

no code implementations6 Aug 2019 Dogancan Temel, Melvin J. Mathew, Ghassan AlRegib, Yousuf M. Khalifa

Based on the conducted experiments, proposed algorithm RAPDNet can achieve a sensitivity and a specificity of 90. 6% over 64 test cases in a balanced set, which corresponds to an AUC of 0. 929 in ROC analysis.

Object Recognition Transfer Learning

Temporal Attentive Alignment for Large-Scale Video Domain Adaptation

5 code implementations ICCV 2019 Min-Hung Chen, Zsolt Kira, Ghassan AlRegib, Jaekwon Yoo, Ruxin Chen, Jian Zheng

Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e. g. 7. 9% accuracy gain over "Source only" from 73. 9% to 81. 8% on "HMDB --> UCF", and 10. 3% gain on "Kinetics --> Gameplay").

Domain Adaptation

Estimation of Acoustic Impedance from Seismic Data using Temporal Convolutional Network

3 code implementations6 Jun 2019 Ahmad Mustafa, Motaz Alfarraj, Ghassan AlRegib

In exploration seismology, seismic inversion refers to the process of inferring physical properties of the subsurface from seismic data.

Learning to Generate Grounded Visual Captions without Localization Supervision

2 code implementations1 Jun 2019 Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib, Peter Vajda, Marcus Rohrbach, Zsolt Kira

When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the model is hallucinating based on priors in the dataset and/or the language model.

Image Captioning Language Modelling +1

Semi-supervised Learning for Acoustic Impedance Inversion

2 code implementations31 May 2019 Motaz Alfarraj, Ghassan AlRegib

Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for acoustic impedance.

Image and Video Processing Signal Processing Geophysics

Temporal Attentive Alignment for Video Domain Adaptation

5 code implementations26 May 2019 Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets.

Domain Adaptation

Multi-level Texture Encoding and Representation (MuLTER) based on Deep Neural Networks

1 code implementation23 May 2019 Yuting Hu, Zhiling Long, Ghassan AlRegib

In this paper, we propose a multi-level texture encoding and representation network (MuLTER) for texture-related applications.

Implicit Background Estimation for Semantic Segmentation

1 code implementation23 May 2019 Charles Lehman, Dogancan Temel, Ghassan AlRegib

Scene understanding and semantic segmentation are at the core of many computer vision tasks, many of which, involve interacting with humans in potentially dangerous ways.

Scene Understanding Semantic Segmentation

Automated Pupillary Light Reflex Test on a Portable Platform

no code implementations21 May 2019 Dogancan Temel, Melvin J. Mathew, Ghassan AlRegib, Yousuf M. Khalifa

In this paper, we introduce a portable eye imaging device denoted as lab-on-a-headset, which can automatically perform a swinging flashlight test.

Structure Label Prediction Using Similarity-Based Retrieval and Weakly-Supervised Label Mapping

no code implementations16 May 2019 Yazeed Alaudah, Motaz Alfarraj, Ghassan AlRegib

By having an interpreter select a very small number of exemplar images for every class of subsurface structures, we use a novel similarity-based retrieval technique to extract thousands of images that contain similar subsurface structures from the seismic volume.

Seismic Interpretation

The Regretful Navigation Agent for Vision-and-Language Navigation

1 code implementation CVPR 2019 (Oral) 2019 Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira

As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making.

Decision Making Vision and Language Navigation +2

Challenging Environments for Traffic Sign Detection: Reliability Assessment under Inclement Conditions

2 code implementations19 Feb 2019 Dogancan Temel, Tariq Alshawi, Min-Hung Chen, Ghassan AlRegib

Experimental results show that benchmarked algorithms are highly sensitive to tested challenging conditions, which result in an average performance drop of 0. 17 in terms of precision and a performance drop of 0. 28 in recall under severe conditions.

Traffic Sign Detection

Object Recognition under Multifarious Conditions: A Reliability Analysis and A Feature Similarity-based Performance Estimation

no code implementations18 Feb 2019 Dogancan Temel, Jinsol Lee, Ghassan AlRegib

Experimental results show that deep learning-based image representations can estimate the recognition performance variation with a Spearman's rank-order correlation of 0. 94 under multifarious acquisition conditions.

Object Recognition

Semantically Interpretable and Controllable Filter Sets

no code implementations17 Feb 2019 Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib

In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion.

Image Quality Assessment

Saliency detection for seismic applications using multi-dimensional spectral projections and directional comparisons

no code implementations30 Jan 2019 Muhammad Amir Shafiq, Zhiling Long, Tariq Alshawi, Ghassan AlRegib

In this paper, we propose a novel approach for saliency detection for seismic applications using 3D-FFT local spectra and multi-dimensional plane projections.

Saliency Detection

Understanding spatial correlation in eye-fixation maps for visual attention in videos

no code implementations30 Jan 2019 Tariq Alshawi, Zhiling Long, Ghassan AlRegib

In this paper, we present an analysis of recorded eye-fixation data from human subjects viewing video sequences.

Characterization of migrated seismic volumes using texture attributes: a comparative study

no code implementations30 Jan 2019 Zhiling Long, Yazeed Alaudah, Muhammad Ali Qureshi, Motaz Al Farraj, Zhen Wang, Asjad Amin, Mohamed Deriche, Ghassan AlRegib

It is our hope that this comparative study will help acquaint the seismic interpretation community with the many available powerful image texture analysis techniques, providing more alternative attributes for their seismic exploration.

Image Retrieval Seismic Interpretation +1

Petrophysical Property Estimation from Seismic Data Using Recurrent Neural Networks

no code implementations24 Jan 2019 Motaz Alfarraj, Ghassan AlRegib

Recent advances in machine learning have shown promising results for recurrent neural networks (RNN) in modeling complex sequential data such as videos and speech signals.

Multiresolution Analysis and Learning for Computational Seismic Interpretation

1 code implementation24 Jan 2019 Motaz Alfarraj, Yazeed Alaudah, Zhiling Long, Ghassan AlRegib

Moreover, directional multiresolution attributes, such as the curvelet transform, are more effective than the non-directional attributes in distinguishing different subsurface structures in large seismic datasets, and can greatly help the interpretation process.

Image and Video Processing Geophysics

A Machine Learning Benchmark for Facies Classification

4 code implementations12 Jan 2019 Yazeed Alaudah, Patrycja Michalowicz, Motaz Alfarraj, Ghassan AlRegib

In addition to making the dataset and the code publicly available, this work helps advance research in this area by creating an objective benchmark for comparing the results of different machine learning approaches for facies classification.

Facies Classification General Classification

SalSi: A new seismic attribute for salt dome detection

no code implementations9 Jan 2019 Muhammad Amir Shafiq, Tariq Alshawi, Zhiling Long, Ghassan AlRegib

In this paper, we propose a saliency-based attribute, SalSi, to detect salt dome bodies within seismic volumes.

Seismic Interpretation

Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection

no code implementations6 Jan 2019 Tariq Alshawi, Zhiling Long, Ghassan AlRegib

Based on the study, we then develop an algorithm that estimates a pixel-wise uncertainty map that reflects our confidence in the associated computational saliency map by relating a pixel's saliency to the saliency of its neighbors.

Video Saliency Detection

The role of visual saliency in the automation of seismic interpretation

no code implementations31 Dec 2018 Muhammad Amir Shafiq, Tariq Alshawi, Zhiling Long, Ghassan AlRegib

In this paper, we propose a workflow based on SalSi for the detection and delineation of geological structures such as salt domes.

Seismic Interpretation

Power of Tempospatially Unified Spectral Density for Perceptual Video Quality Assessment

2 code implementations12 Dec 2018 Mohammed A. Aabed, Gukyeong Kwon, Ghassan AlRegib

This is a full-reference tempospatial approach that considers both temporal and spatial PSD characteristics.

Video Quality Assessment

Image Quality Assessment and Color Difference

1 code implementation22 Nov 2018 Dogancan Temel, Ghassan AlRegib

In this work, we combine these approaches by extending CIEDE2000 formula with perceptual color difference to assess image quality.

Image Quality Assessment MS-SSIM +1

A Comparative Study of Quality and Content-Based Spatial Pooling Strategies in Image Quality Assessment

1 code implementation21 Nov 2018 Dogancan Temel, Ghassan AlRegib

In this work, we compare the state of the art quality and content-based spatial pooling strategies and show that although features are the key in any image quality assessment, pooling also matters.

Image Quality Assessment SSIM

Generating Adaptive and Robust Filter Sets Using an Unsupervised Learning Framework

no code implementations21 Nov 2018 Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

While assessing image quality, the filters need to capture perceptual differences based on dissimilarities between a reference image and its distorted version.

Image Quality Assessment

Boosting in Image Quality Assessment

1 code implementation21 Nov 2018 Dogancan Temel, Ghassan AlRegib

In addition to support vector machines that are commonly used in the multi-method fusion, we propose using neural networks in the boosting.

Image Quality Assessment

A Comparative Study of Computational Aesthetics

no code implementations19 Nov 2018 Dogancan Temel, Ghassan AlRegib

We show that generic descriptors can perform as well as state of the art hand-crafted aesthetics models that use global features.

BLeSS: Bio-inspired Low-level Spatiochromatic Similarity Assisted Image Quality Assessment

1 code implementation16 Nov 2018 Dogancan Temel, Ghassan AlRegib

Moreover, BleSS significantly enhances the performance of SR-SIM and FSIM in the full TID 2013 database.

Image Quality Assessment

ReSIFT: Reliability-Weighted SIFT-based Image Quality Assessment

1 code implementation14 Nov 2018 Dogancan Temel, Ghassan AlRegib

In terms of the Pearson and the Spearman correlation, ReSIFT is the best performing quality estimator in the overall databases.

Image Quality Assessment

Content-adaptive non-parametric texture similarity measure

1 code implementation5 Nov 2018 Motaz Alfarraj, Yazeed Alaudah, Ghassan AlRegib

In this paper, we introduce a non-parametric texture similarity measure based on the singular value decomposition of the curvelet coefficients followed by a content-based truncation of the singular values.

Image and Video Processing

HeartBEAT: Heart Beat Estimation through Adaptive Tracking

1 code implementation19 Oct 2018 Huijie Pan, Dogancan Temel, Ghassan AlRegib

In this paper, we propose an algorithm denoted as HeartBEAT that tracks heart rate from wrist-type photoplethysmography (PPG) signals and simultaneously recorded three-axis acceleration data.

Photoplethysmography (PPG)

CURE-OR: Challenging Unreal and Real Environments for Object Recognition

no code implementations18 Oct 2018 Dogancan Temel, Jinsol Lee, Ghassan AlRegib

Moreover, we investigate the relationship between object recognition and image quality and show that objective quality algorithms can estimate recognition performance under certain photometric challenging conditions.

Object Recognition

CSV: Image Quality Assessment Based on Color, Structure, and Visual System

no code implementations15 Oct 2018 Dogancan Temel, Ghassan AlRegib

This paper presents a full-reference image quality estimator based on color, structure, and visual system characteristics denoted as CSV.

Image Quality Assessment

Perceptual Image Quality Assessment through Spectral Analysis of Error Representations

no code implementations14 Oct 2018 Dogancan Temel, Ghassan AlRegib

To overcome these shortcomings, we introduce an image quality assessment algorithm based on the Spectral Understanding of Multi-scale and Multi-channel Error Representations, denoted as SUMMER.

Image Quality Assessment

CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition

1 code implementation7 Dec 2017 Dogancan Temel, Gukyeong Kwon, Mohit Prabhushankar, Ghassan AlRegib

We benchmark the performance of existing solutions in real-world scenarios and analyze the performance variation with respect to challenging conditions.

Data Augmentation Traffic Sign Recognition

Grounded Objects and Interactions for Video Captioning

no code implementations16 Nov 2017 Chih-Yao Ma, Asim Kadav, Iain Melvin, Zsolt Kira, Ghassan AlRegib, Hans Peter Graf

We address the problem of video captioning by grounding language generation on object interactions in the video.

Scene Understanding Text Generation +2

TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition

4 code implementations30 Mar 2017 Chih-Yao Ma, Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.

Action Classification Action Recognition +1

Cannot find the paper you are looking for? You can Submit a new open access paper.