Topics

<> Computer Vision (46)

Karen Sanchez

Postdoctoral Research Fellow
Karen Sanchez is a Postdoctoral Researcher in the IVUL lab at KAUST, specializing in deep learning, machine learning, and artificial intelligence (AI) for healthcare applications. Her research focuses on video understanding, domain adaptation, generative AI, and methods for preserving patient privacy.

Aznaur Aliev

M.S. Student

Hani A. Al Majed

M.S. Student
Electrical and Computer Engineering Master's student at KAUST under the supervision of Professor Bernard Ghanem, with expertise in machine learning workflow automation, physics-informed neural operators, and AI for Science, particularly in chemistry applications. Passionate about leveraging AI to solve complex scientific problems.

Ahmad Sait

M.S. Student, Computer Science
Ahmad Sait is a Master's student in the Computer Science program at KAUST. Before joining KAUST, Ahmad obtained his Bachelor's degree in Computer Science from King Abdulaziz University, Saudi Arabia. Ahmad is also a KAUST Academy graduate from the AI track, having been under the supervision of Prof. Naeemullah Khan. The Academy provided him with seven opportunities to assist in teaching students enrolled in subsequent cohorts.

Sim-to-Real Transfer for Autonomous Navigation

-

B2 L5 R5220

This work investigates the problem of transfer from simulation to the real world in the context of autonomous navigation. To this end, we first present a photo-realistic training and evaluation simulator Sim4CV which enables several applications across various fields of computer vision. Built on top of the Unreal Engine, the simulator features cars and unmanned aerial vehicles (UAVs) with a realistic physics simulation and diverse urban and suburban 3D environments. We demonstrate the versatility of the simulator with two case studies: autonomous UAV-based tracking of moving objects and autonomous driving using supervised learning.

Efficient Localization of Human Actions and Moments in Videos

-

B3 L5 R5220

Abstract We are stumbling across a video tsunami flooding our communication channels. The ubiquity of digital cameras and social networks has increased the amount of visual media content generated and shared by people, in particular videos. Cisco reports that 82% of the internet traffic would be in the form of videos by 2022. The computer vision community has embraced this challenge by offering the first building blocks to translate the visual data in segmented video clips into semantic tags. However, users usually require to go beyond tagging at the video level. For example, someone may want

Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives

-

KAUST

In this dissertation, we aim at theoretically studying and analyzing deep learning models. Since deep models substantially vary in their shapes and sizes, in this dissertation, we restrict our work to a single fundamental block of layers that is common in almost all architectures. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation function and then lastly followed by another affine layer. We study this block of layers from three different perspectives. (i) An Optimization Perspective. We try addressing the following question: Is it possible that the output of the forward pass through the block of layers highlighted above is an optimal solution to a certain convex optimization problem? As a result, we show an equivalency between the forward pass through this block of layers and a single iteration of certain types of deterministic and stochastic algorithms solving a particular class of tensor formulated convex optimization problems.

Indoor 3D Scene Understanding Using Depth Sensors

-

KAUST

One of the main goals in computer vision is to achieve a human-like understanding of images. This understanding has been recently represented in various forms, including image classification, object detection, semantic segmentation, among many others. Nevertheless, image understanding has been mainly studied in the 2D image frame, so more information is needed to relate them to the 3D world. With the emergence of 3D sensors (e.g. the Microsoft Kinect), which provide depth along with color information, the task of propagating 2D knowledge into 3D becomes more attainable and enables interaction between a machine (e.g. robot) and its environment. This dissertation focuses on three aspects of indoor 3D scene understanding: (1) 2D-driven 3D object detection for single frame scenes with inherent 2D information, (2) 3D object instance segmentation for 3D reconstructed scenes, and (3) using room and floor orientation for automatic labeling of indoor scenes that could be used for self-supervised object segmentation. These methods allow capturing of physical extents of 3D objects, such as their sizes and actual locations within a scene.

Towards Richer Video Representation for Action Understanding

-

B2 L5 R5209

With video data dominating the internet traffic, it is crucial to develop automated models that can analyze and understand what humans do in videos. Such models must solve tasks such as action classification, temporal activity localization, spatiotemporal action detection, and video captioning. This dissertation aims to identify the challenges hindering the progress in human action understanding and propose novel solutions to overcome these challenges.

Best Business Plan at VIEW 2016

1 min read ·
Hachid won the award for the Venture pitch with the best business plan at the Fifth Annual Vision Industry and Entrepreneur Workshop (VIEW) 2016.

Fabian and Victor participate in the annual MSR Summer School!

1 min read ·
Two IVUL Ph.D. students (Fabian Caba and Victor Escorcia) participate in the annual MSR Summer School.

Adel Bibi and Matthias Mueller going to ICVSS 2017

1 min read ·
Adel Bibi and Matthias Mueller have been accepted to participate in the ICVSS (International Computer Vision Summer Schoole) 2017 in Italy. Admission into this summer school is quite competitive in the vision community.​​​

Prof. Bernard Ghanem to give a talk at Machines Can See 2021

1 min read ·
The fifth annual international summit ‘Machines Can See’ will host IVUL's own Prof. Bernard Ghanem as a speaker. The summit, to be held on July 8th 2021, is hosted by VisionLabs, a leading software company devoted to developing products based on state-of-the-art Computer Vision algorithms. The summit will be a space for Computer Vision and Machine Learning leading experts to discuss technology trends and share experience regarding human-centric technologies. Together with Prof. Bernard Ghanem, the summit will feature Professors Dima Damen, Efstratios Gavves, Ira Kemelmacher-Shlizerman, and

Seven IVUL members recognized as Outstanding Reviewers by CVPR 2021

1 min read ·
The 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) has granted Outstanding Reviewer awards to seven members of IVUL: Alejandro Pardo, Ali Thabet, Chen Zhao, Mattia Soldan, Mengmeng Xu, Juan C. Pérez, and Silvio Giancola. CVPR, a premier annual computer vision event that will take place virtually from June 19th to June 25th, is the largest computer vision conference in the world, gathering researchers from academia and industry alike. The peer-review process through which the conference determines acceptance of papers relies on expert reviewers from across the world

IVUL paper Wins Best Poster award at CVPR Workshop

1 min read ·
A paper by IVUL members won a Best Poster award at the LatinX in Computer Vision Workshop at CVPR 2021, the world-renowned venue for research in Computer Vision. The paper, "BAOD: Budget-Aware Object Detection", was written by four IVUL members, Alejandro Pardo, Mengmeng Frost Xu, Ali K. Thabet, and Bernard Ghanem, in collaboration with Professor Pablo Arbeláez, from Universidad de los Andes. The paper studies the efficiency with which object-detection systems learn when constrained by limited budgets. We congratulate the authors!

Victor Escorcia

Research Scientist committed to innovating AI agents to empower creativity and increase productivity. Passionate about developing cutting-edge AI applications involving video understanding and creative storytelling. I have a wide range of research and engineering interests from on-device AI to General AI. Reach out!

Silvio Giancola

Silvio Giancola is a Research Scientist at King Abdullah University of Science and Technology (KAUST), under the supervision of Prof. Bernard Ghanem in the Image and Video Understanding Laboratory (IVUL), part of the Center of Excellence for Generative AI (GenAI).

Shuming Liu

Ph.D. Student, Computer Science
Shuming Liu is a Ph.D. student in the computer science program at the Image and Video Understanding Lab (IVUL), King Abdullah University of Science and Technology (KAUST), under the supervision of Professor Bernard Ghanem.

Sara Rojas Martinez

Sara Rojas Martinez is a Ph.D. student in the KAUST Image and Video Understanding Lab (IVUL) under the supervision of Professor Bernard Ghanem. Before joining KAUST, Sara obtained a master’s degree in Biomedical Engineering from Universidad de Los Andes, Bogotá, Colombia. Research Interests Sara is interested in topics related to the investigation in Artificial Intelligence and Computer Vision. . Education Profile • M.S., Biomedical Engineering, University of Los Andes, Colombia, 2018 • B.E., Artificial Intelligence in Electronics Engineering, University of Los Andes, Colombia, 2017

Sara Shaheen

Sara Shaheen was a Ph.D. student in Computer Science under the supervision of Professor Bernard Ghanem at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST). She is currently an Assistant Professor in Computer Science at Prince Sultan University (PSU) in Riyadh, Saudi Arabia. Education and Career Sara received her Bachelor degree in Computer Science from Prince Sultan University (PSU) in Riyadh in 2010. She joined the MS/PhD program in KAUST and earned her Master and Ph.D. in Computer Science in 2017. She was a part of Image and Video Understanding

Salman Alsubaihi

Salman Alsubaihi was an Electrical and Computer Engineering Master Student in the Image and Video Understanding Lab (IVUL) under the supervision of Professor Bernard Ghanem at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Early Career Salman Alsubaihi obtained his bachelor degree in Electrical Engineering from King Fahd University of Petroleum and Minerals (KFUPM) in Saudi Arabia in 2017. In 2019, he received his Master in Electrical Engineering from KAUST. Research Interests ​ Salman is focusing on understanding deep neural

Noor Bafageeh

Noor Bafageeh was a Master student in Computer Science Program under the supervision of Professor Bernard Ghanem at Visual Computing Center (VCC) at King Abdullah university of Science and Technology (KAUST). Education and Career Noor earned her bachelor degree in Computer Science from Effat University in Jeddah in 2016. She joined KAUST and received her master degree in Computer Science in 2018. Research Interest She is interested in computer vision, machine learning, Generative Adversarial Networks (GAN) and deep learning. Education Profile M.S., Computer Science, King Abdullah University of

Motasem Alfarra

Motasem Alfarra is an Electrical and Computer Engineering Ph.D. student in Image and Video Understanding Lab (IVUL) Group in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem.

Modar Alfadly

Ph.D. Student, Computer Science
Modar Alfadly is a Ph. D. candidate in Image and Video Understanding Lab (IVUL) Group under the supervision of Prof. Bernard Ghanem at KAUST. Education and Early Career Alfadly received his bachelor’s degree in Software Engineering from King Fahd University of Petroleum and Minerals (KFUPM) in 2016. A year later, he obtained his master’s degree in Computer Science and successfully defended his thesis, titled “Analytic Treatment of Deep Neural Networks under Additive Gaussian Noise”. Research Interest Modar Alfadly is focusing on understanding deep neural networks to build more intelligent

Merey Ramazanova

Ph.D. Student, Computer Science
Merey Ramazanova is a Computer Science Ph.D. Student in Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career Merey obtained her bachelor's degree in Computer Science from Nazarbayev University in Kazakhstan in 2018. She also was a Research Intern at Okinawa Institute of Science and Technology (OIST) in Okinawa, Japan in 2018. Research Interest She is focusing on her research on data science, computer vision, and machine learning. Education Profile M.S., Computer

Mengmeng Xu (Frost)

Mengmeng Xu (Frost) was an Electrical and Computer Engineering PhD Student in Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. He is currently continuing his Ph.D. Education and Early Career Mengmeng obtained his bachelor's degree in Optics and Optical Sciences from Zhejiang University in China in 2017 and his Master's Degree from KAUST under the supervision of Professor Bernard Ghanem. Research Interests He is mainly focusing on problems that arise in computer vision, including

Matthias Mueller

Matthias Mueller was an Electrical and Computer Engineering Ph.D. candidate in Image and Video Understanding Lab (IVUL) Group at Visual Computing Center (VCC) under the supervision of Prof. Bernard Ghanem at King Abdullah University of Science and Technology (KAUST). Education and Early Career Matthias graduated with a B.Sc. in Electrical Engineering and Math Minor from Texas A&M University in 2011. After graduation, he joined P+Z Engineering in Munich, Germany as an Electrical Engineer and worked for 3 years on the development of mild-hybrid electric machines at BMW. In 2014, he started his M

Lama Alssum

Ph.D. Student, Computer Science
Lama Alssum is a Ph.D. student in Computer Science under the supervision of Professor Bernard Ghanem in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Early Career Lama studied Information technology at King Saud University (KSU) in Riyadh and graduated with a Bachelor degree in 2011. After her bachelor degree, she joined KSU as a Teaching Assistant. Later on, she continued her studies and earned her Master degree in Computer Science from the School of Computing Science at the University of Glasgow, United Kingdom. Lama first joined

Kumail Alhamoud

M.S. Student, Computer Science
Kumail Alhamoud is a Computer Science M.S Student at KAUST working under the supervision of Professor Bernard Ghanem at the Image and Video Understanding Lab (IVUL). Before joining KAUST, Kumail obtained his B.S in Electrical and Computer Engineering at Cornell University in 2021. His current research interests include continual learning, learning from limited data under distribution shifts, and AI for Science and Biomedicine. Publications

Juan C. Pérez

Ph.D. Student, Computer Science
Juan C. Pérez is a Ph.D. Candidate in the computer science program under Professor Bernard Ghanem's supervision at the Image and Video Understanding Lab at King Abdullah University of Science and Technology (KAUST). Before joining KAUST, Juan obtained a master's degree and a bachelor's degree ( cum laude) in biomedical engineering from Universidad de Los Andes, Colombia.

Jia-Hong Huang

Jia-Hong Huang was a Master's student in the Electrical and Computer Engineering Program under the supervision of Professor Bernard Ghanem at Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Career Jia-Hong earned a double major bachelor's degree in Statistics and Mathematical Science from National Chengchi University in Taiwan in 2014. He received his master's degree in Mechanical Engineering from National Taiwan University in 2016. After that, he joined KAUST and received his second master's degree in Electrical Engineering in 2018

Jean Lahoud

Jean Lahoud was a Ph. D. student in Image and Video Understanding Lab (IVUL) Group under the supervision of Prof. Bernard Ghanem at KAUST. Education and Early Career Jean Lahoud received his Bachelor of Engineering in Mechanical Engineering from Notre Dame University in Lebanon in 2012. In 2014, he obtained his Master of Engineering degree in the same field from American University of Beirut in Lebanon. Before joining KAUST, Jean was a product manager at Murex systems in Lebanon. Research Interest Jean Lahoud is interested in 3​D scene understanding using RGB-D sensors. Honors and Awards In

Jesus Zarzar

Jesus Zarzar is an Electrical and Computer Engineering PhD student in Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career Jesus obtained his bachelor degree in Electrical and Computer Engineering from UT Austin, United States in 2017 before obtaining his Master's Degree from KAUST under the supervision of Professor Bernard Ghanem. Publications Education Profile ​B.S., Electrical and Computer Engineering, UT Austin, Austin, United States, 2017

Humam Alwassel

Ph.D. Student, Computer Science
Humam Alwassel is a Computer Science Ph.D. candidate in Image and Video Understanding Lab (IVUL) Group under the supervision of Professor Bernard Ghanem at King Abdullah University of Science and Technology (KAUST). Education and Early Career Humam obtained his bachelor degree with double major in Computer Science and Mathematics from Cornell University in New York, USA in 2016. After that, he joined KAUST for the MS/PhD program and received his master degree in Computer Science in 2018. Research Interest He’s currently focused on the development of novel computer vision techniques for video

Hasan Abed Al Kader Hammoud

Hasan is an Electrical and Computer Engineering MS/Ph.D. student in Image and Video Understanding Lab (IVUL) Group in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career Hasan obtained his bachelor's degree in Electrical and Computer Engineering from American University of Beirut in 2020. He joined KAUST in 2020 to pursue his MS and PhD degrees. Research Interest Deep Learning Machine Learning Computer Vision Publications Rapid Adaptation in Online Continual Learning: Are We

Gordon Guocheng Qian

Guocheng Qian is currently working towards an MS/Ph.D. degree in the Department of Computer Science at King Abdullah University of Science and Technology (KAUST). He is part of the Image and Video Understanding Lab (IVUL), supervised by Prof. Bernard Ghanem. During his Ph.D. studies, he interned at several leading institutions including Snap Research, Meta Reality Lab, and MEGVII research. His primary research interest lies in 3D vision. Education and Early Career Guocheng obtained his bachelor's degree in Engineering with first-class honors from Xi’an Jiaotong University (XJTU) in China in

Guohao Li

Ph.D. Student, Computer Science
Guohao Li is a Ph. D. candidate in Image and Video Understanding Lab (IVUL) Group under the supervision of Prof. Bernard Ghanem at KAUST. Education and Early Career Guohao Li obtained a Bachelor’s Degree in Communication Engineering from Harbin Institute of Technology in China in 2015. In 2018, he received his Master Degree in Communication and Information System from Chinese Academy of Science in China. Research Interest His primary research interest is in Computer Vision and Deep Learning. Publications Education Profile M.Sc. in Communication and Information System, Chinese Academy of

Frankly Toro

Frankly Toro is a Ms/Ph.D. student under the supervision of Prof. Bernard Ghanem at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST). Education and Early Career He is a graduate of National University of Colombia where he received a B.S. degree in Mechatronics. Education Profile B.S., Mechatronics , National University of Colombia, 2020

Fabian Heilbron

Fabian Caba Heilbron was a Ph.D. student in Image and Video Understanding Lab (IVUL) Group under the supervision of Prof. Bernard Ghanem at King Abdullah University of Science and Technology (KAUST). He is currently a Research Scientist at Adobe Research in San Jose, California. Educ ation and Early Career Fabian has a Bachelor’s Degree in Electronics Engineering from Universidad del Norte in Barranquilla, Colombia, 2011. In 2013, he received his Master Degree in Electronics Engineering from Universidad del Norte in Barranquilla, Colombia. He joined KAUST as a Ph.D. candidate and received his

Chen Zhao

Chen Zhao is a Research Scientist at KAUST, and Lead of the Video Understanding Theme in the Image and Video Understanding Lab. She received her Ph.D. degree from Peking University, China in 2016. She studied in University of Washington, US from 2012 to 2013, and at the National Institute of Informatics, Japan in 2016. She has published 40+ papers on representative journals and conferences such as TPAMI, CVPR, ICCV, ECCV, and has received over 3000 citations according to Google Scholar.

Cheng Zheng

Cheng Zheng is a Software Engineer Consultant working with Professor Bernard Ghanem in the Image and Video Understanding Lab (IVUL) in the Visual Computing Center at King Abdullah University of Science and Technology (KAUST). Education and Early Career Cheng Zheng received his Bachelor's degree in Computer Science from Beijing University of Posts and Telecommunications (BUPT), China, in 2009. He received his Master's degree from the University of Chinese Academy of Sciences (UCAS), China, In 2012. Before joining KAUST, in 2012, he worked as a software engineer at NetEase Games in China. In

Carlos Hinojosa Montero

Postdoctoral Research Fellow, Image and Video Understanding Lab
Education and Early Career o Bachelor of System Engineering and Informatics, University: Universidad Industrial de Santander, 2011-2015. o Master of Science in Computer and System Engineering, University: Universidad Industrial de Santander, 2016-2018. o PhD in Computer Science, University: Universidad Industrial de Santander, 2017-2022.

Ali Thabet

Ali Thabet is a Research Scientist at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST), working with Professor Bernard Ghanem in the Image and Video Understanding Laboratory (IVUL). Education and Early Career Ali obtained a bachelor of engineering degree in Electrical Engineering, from the American University of Beirut in Beirut, Lebanon in 2006. He holds a ​Ph.D. in Computer Science from the University of Dundee in Dundee, UK. He joined KAUST as a Postdoctoral Fellow in the Visual Computing Center (VCC) from 2012 to 2014. After that, he worked as

Alejandro Pardo

Alejandro Pardo is a Ph.D. candidate in the Electrical and Computer Engineering (ECE) program under the supervision of Professor Bernard Ghanem at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) in Saudi Arabia. Education and Early Career Alejandro has an Engineer’s degree in Artificial Intelligence in both Electronics and Biomedical Engineering from the University of Los Andes in Colombia in 2017. He continued his studies at the University of Los Andes and received his Master’s Degree in Biomedical Engineering in 2018. He visited KAUST as a

Adel Bibi

Adel Bibi is a postdoctoral research assistant in computer vision and machine learning at the Torr Vision Group working with Professor Philip Torr at the University of Oxford. Prior to that, he received his MSc and PhD degrees from King Abdullah University of Science & Technology (KAUST) where he was part of the Image and Video Understanding Lab (IVUL) advised by Professor Bernard Ghanem. Education and Early Career Adel Bibi has a Bachelor’s Degree in Electrical Engineering from Kuwait University in 2014. He received his Master Degree in Electrical Engineering from King Abdullah University of

Abdullah Hamdi

Abdullah Hamdi is a Ph.D. candidate in Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career In 2016, Abdullah Hamdi obtained his bachelor degree in Electrical Engineering from King Fahd University of Petroleum and Minerals (KFUPM) in Dhahran, Saudi Arabia. After that, he joined KAUST to proceed in the same field of study and received his master degree in 2017 in Computer Vision track. Research Interest Machine Learning Robustness of Deep Learning Computer Vision
<> machine learning (35)

Hayssam Dahrouj

Senior Research Scientist at KAUST (King Abdullah University of Science and Technology)

Karen Sanchez

Postdoctoral Research Fellow
Karen Sanchez is a Postdoctoral Researcher in the IVUL lab at KAUST, specializing in deep learning, machine learning, and artificial intelligence (AI) for healthcare applications. Her research focuses on video understanding, domain adaptation, generative AI, and methods for preserving patient privacy.

Hani A. Al Majed

M.S. Student
Electrical and Computer Engineering Master's student at KAUST under the supervision of Professor Bernard Ghanem, with expertise in machine learning workflow automation, physics-informed neural operators, and AI for Science, particularly in chemistry applications. Passionate about leveraging AI to solve complex scientific problems.

Ahmad Sait

M.S. Student, Computer Science
Ahmad Sait is a Master's student in the Computer Science program at KAUST. Before joining KAUST, Ahmad obtained his Bachelor's degree in Computer Science from King Abdulaziz University, Saudi Arabia. Ahmad is also a KAUST Academy graduate from the AI track, having been under the supervision of Prof. Naeemullah Khan. The Academy provided him with seven opportunities to assist in teaching students enrolled in subsequent cohorts.

Saleh AlJazzar

Research Fellow at King Abdullah University of Science and Technology (KAUST) .

Muhammad Esmat

Visiting student at, King Abdullah University of Science and Technology (KAUST).

Yasser Jaber

Visiting Student Researcher ,Machine Learning Engineer at KAUST (King Abdullah University of Science and Technology).
Syed Abidullah Fareed

Syed Abidullah Fareed

Visiting Student (former), Information Science Lab

Ahsan Mehmood

Intern (former), Information Science Lab
Visiting student at King Abdullah University of Science and Technology (KAUST).

Abdulkarem Badiea Alshaibani

Visiting Student at the Information Science Lab at the King Abdullah University of Science and Technology (KAUST).

ML Hub Seminar Series | The Machine Learning (ML) Hub

-

B9 H2 R2325

The Machine Learning Hub @ KAUST is designed to be the one-stop-shop for machine learning (ML) and artificial intelligence (AI) at KAUST. It is an informal forum for exchanging ideas in these areas, including (but not limited to) theoretical foundations, systems, tools, and applications. It will be providing several offerings to the KAUST community interested in ML and AI, including a regular seminar series where new research in the field is presented, an online social forum dedicated to AI and ML discussions, announcements, brainstorming, collaborations, and hands-on activities (e.g

Sim-to-Real Transfer for Autonomous Navigation

-

B2 L5 R5220

This work investigates the problem of transfer from simulation to the real world in the context of autonomous navigation. To this end, we first present a photo-realistic training and evaluation simulator Sim4CV which enables several applications across various fields of computer vision. Built on top of the Unreal Engine, the simulator features cars and unmanned aerial vehicles (UAVs) with a realistic physics simulation and diverse urban and suburban 3D environments. We demonstrate the versatility of the simulator with two case studies: autonomous UAV-based tracking of moving objects and autonomous driving using supervised learning.

Efficient Localization of Human Actions and Moments in Videos

-

B3 L5 R5220

Abstract We are stumbling across a video tsunami flooding our communication channels. The ubiquity of digital cameras and social networks has increased the amount of visual media content generated and shared by people, in particular videos. Cisco reports that 82% of the internet traffic would be in the form of videos by 2022. The computer vision community has embraced this challenge by offering the first building blocks to translate the visual data in segmented video clips into semantic tags. However, users usually require to go beyond tagging at the video level. For example, someone may want

Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives

-

KAUST

In this dissertation, we aim at theoretically studying and analyzing deep learning models. Since deep models substantially vary in their shapes and sizes, in this dissertation, we restrict our work to a single fundamental block of layers that is common in almost all architectures. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation function and then lastly followed by another affine layer. We study this block of layers from three different perspectives. (i) An Optimization Perspective. We try addressing the following question: Is it possible that the output of the forward pass through the block of layers highlighted above is an optimal solution to a certain convex optimization problem? As a result, we show an equivalency between the forward pass through this block of layers and a single iteration of certain types of deterministic and stochastic algorithms solving a particular class of tensor formulated convex optimization problems.

Towards Richer Video Representation for Action Understanding

-

B2 L5 R5209

With video data dominating the internet traffic, it is crucial to develop automated models that can analyze and understand what humans do in videos. Such models must solve tasks such as action classification, temporal activity localization, spatiotemporal action detection, and video captioning. This dissertation aims to identify the challenges hindering the progress in human action understanding and propose novel solutions to overcome these challenges.

Student Focus: Adel Bibi

1 min read ·
KAUST Ph.D. student Adel Bibi, who works on bridging the gap between theory and practice in deep learning, believes we're living in a very exciting time.

Testing the blind spots in artificial intelligence

1 min read ·
Understanding the situations when artificial intelligence can fail is critical for application of future autonomous vehicles and medical diagnostics.

Professor Ghanem wins 2020 Abdul Hameed Shoman Award for Arab Researchers

1 min read ·
Bernard Ghanem, KAUST associate professor of electrical and computer engineering and computer science, recently received the 2020 Abdul Hameed Shoman Award for Arab Researchers for ''Machine Learning and Big Data.''

Yibo Yang

Research Scientist
Yibo Yang is a research scientist at the Image and Video Understanding Lab (IVUL) under the supervision of Professor Bernard Ghanem. Before joining KAUST, he obtained his Ph.D. from Peking University in 2021. He worked as a researcher at JD Explore Academy, JD.com, in 2021-2023.

Salman Alsubaihi

Salman Alsubaihi was an Electrical and Computer Engineering Master Student in the Image and Video Understanding Lab (IVUL) under the supervision of Professor Bernard Ghanem at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Early Career Salman Alsubaihi obtained his bachelor degree in Electrical Engineering from King Fahd University of Petroleum and Minerals (KFUPM) in Saudi Arabia in 2017. In 2019, he received his Master in Electrical Engineering from KAUST. Research Interests ​ Salman is focusing on understanding deep neural

Noor Bafageeh

Noor Bafageeh was a Master student in Computer Science Program under the supervision of Professor Bernard Ghanem at Visual Computing Center (VCC) at King Abdullah university of Science and Technology (KAUST). Education and Career Noor earned her bachelor degree in Computer Science from Effat University in Jeddah in 2016. She joined KAUST and received her master degree in Computer Science in 2018. Research Interest She is interested in computer vision, machine learning, Generative Adversarial Networks (GAN) and deep learning. Education Profile M.S., Computer Science, King Abdullah University of

Motasem Alfarra

Motasem Alfarra is an Electrical and Computer Engineering Ph.D. student in Image and Video Understanding Lab (IVUL) Group in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem.

Modar Alfadly

Ph.D. Student, Computer Science
Modar Alfadly is a Ph. D. candidate in Image and Video Understanding Lab (IVUL) Group under the supervision of Prof. Bernard Ghanem at KAUST. Education and Early Career Alfadly received his bachelor’s degree in Software Engineering from King Fahd University of Petroleum and Minerals (KFUPM) in 2016. A year later, he obtained his master’s degree in Computer Science and successfully defended his thesis, titled “Analytic Treatment of Deep Neural Networks under Additive Gaussian Noise”. Research Interest Modar Alfadly is focusing on understanding deep neural networks to build more intelligent

Merey Ramazanova

Ph.D. Student, Computer Science
Merey Ramazanova is a Computer Science Ph.D. Student in Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career Merey obtained her bachelor's degree in Computer Science from Nazarbayev University in Kazakhstan in 2018. She also was a Research Intern at Okinawa Institute of Science and Technology (OIST) in Okinawa, Japan in 2018. Research Interest She is focusing on her research on data science, computer vision, and machine learning. Education Profile M.S., Computer

Matthias Mueller

Matthias Mueller was an Electrical and Computer Engineering Ph.D. candidate in Image and Video Understanding Lab (IVUL) Group at Visual Computing Center (VCC) under the supervision of Prof. Bernard Ghanem at King Abdullah University of Science and Technology (KAUST). Education and Early Career Matthias graduated with a B.Sc. in Electrical Engineering and Math Minor from Texas A&M University in 2011. After graduation, he joined P+Z Engineering in Munich, Germany as an Electrical Engineer and worked for 3 years on the development of mild-hybrid electric machines at BMW. In 2014, he started his M

Lama Alssum

Ph.D. Student, Computer Science
Lama Alssum is a Ph.D. student in Computer Science under the supervision of Professor Bernard Ghanem in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Early Career Lama studied Information technology at King Saud University (KSU) in Riyadh and graduated with a Bachelor degree in 2011. After her bachelor degree, she joined KSU as a Teaching Assistant. Later on, she continued her studies and earned her Master degree in Computer Science from the School of Computing Science at the University of Glasgow, United Kingdom. Lama first joined

Kumail Alhamoud

M.S. Student, Computer Science
Kumail Alhamoud is a Computer Science M.S Student at KAUST working under the supervision of Professor Bernard Ghanem at the Image and Video Understanding Lab (IVUL). Before joining KAUST, Kumail obtained his B.S in Electrical and Computer Engineering at Cornell University in 2021. His current research interests include continual learning, learning from limited data under distribution shifts, and AI for Science and Biomedicine. Publications

Jia-Hong Huang

Jia-Hong Huang was a Master's student in the Electrical and Computer Engineering Program under the supervision of Professor Bernard Ghanem at Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Career Jia-Hong earned a double major bachelor's degree in Statistics and Mathematical Science from National Chengchi University in Taiwan in 2014. He received his master's degree in Mechanical Engineering from National Taiwan University in 2016. After that, he joined KAUST and received his second master's degree in Electrical Engineering in 2018

Humam Alwassel

Ph.D. Student, Computer Science
Humam Alwassel is a Computer Science Ph.D. candidate in Image and Video Understanding Lab (IVUL) Group under the supervision of Professor Bernard Ghanem at King Abdullah University of Science and Technology (KAUST). Education and Early Career Humam obtained his bachelor degree with double major in Computer Science and Mathematics from Cornell University in New York, USA in 2016. After that, he joined KAUST for the MS/PhD program and received his master degree in Computer Science in 2018. Research Interest He’s currently focused on the development of novel computer vision techniques for video

Hasan Abed Al Kader Hammoud

Hasan is an Electrical and Computer Engineering MS/Ph.D. student in Image and Video Understanding Lab (IVUL) Group in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career Hasan obtained his bachelor's degree in Electrical and Computer Engineering from American University of Beirut in 2020. He joined KAUST in 2020 to pursue his MS and PhD degrees. Research Interest Deep Learning Machine Learning Computer Vision Publications Rapid Adaptation in Online Continual Learning: Are We

Fabian Heilbron

Fabian Caba Heilbron was a Ph.D. student in Image and Video Understanding Lab (IVUL) Group under the supervision of Prof. Bernard Ghanem at King Abdullah University of Science and Technology (KAUST). He is currently a Research Scientist at Adobe Research in San Jose, California. Educ ation and Early Career Fabian has a Bachelor’s Degree in Electronics Engineering from Universidad del Norte in Barranquilla, Colombia, 2011. In 2013, he received his Master Degree in Electronics Engineering from Universidad del Norte in Barranquilla, Colombia. He joined KAUST as a Ph.D. candidate and received his

Bernard Ghanem

Professor Ghanem's research focuses on computer vision and machine learning, emphasizing large-scale video understanding, vision for automated navigation and theoretical foundations.

Adel Bibi

Adel Bibi is a postdoctoral research assistant in computer vision and machine learning at the Torr Vision Group working with Professor Philip Torr at the University of Oxford. Prior to that, he received his MSc and PhD degrees from King Abdullah University of Science & Technology (KAUST) where he was part of the Image and Video Understanding Lab (IVUL) advised by Professor Bernard Ghanem. Education and Early Career Adel Bibi has a Bachelor’s Degree in Electrical Engineering from Kuwait University in 2014. He received his Master Degree in Electrical Engineering from King Abdullah University of

Abdulellah Abualshour

Abdulellah Abualshour is a Ph.D. student under the supervision of Prof. Bernard Ghanem at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST). Education and Early Career Abdulellah was chosen to join the KAUST Gifted Student Program (KGSP). He is a graduate of Rutgers University where he received a B.S. degree in Computer Science, with a focus on data science and artificial intelligence. Regarding his early career, Abdulellah did many internships during his studies. In 2015, he worked for 1 year as a Public Relations Officer at Rutgers U niversity in

Abdullah Hamdi

Abdullah Hamdi is a Ph.D. candidate in Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career In 2016, Abdullah Hamdi obtained his bachelor degree in Electrical Engineering from King Fahd University of Petroleum and Minerals (KFUPM) in Dhahran, Saudi Arabia. After that, he joined KAUST to proceed in the same field of study and received his master degree in 2017 in Computer Vision track. Research Interest Machine Learning Robustness of Deep Learning Computer Vision
<> Deep learning (27)

Karen Sanchez

Postdoctoral Research Fellow
Karen Sanchez is a Postdoctoral Researcher in the IVUL lab at KAUST, specializing in deep learning, machine learning, and artificial intelligence (AI) for healthcare applications. Her research focuses on video understanding, domain adaptation, generative AI, and methods for preserving patient privacy.

Mhd. Emad Alolaby

Sixiu Liu

Ph.D. degree in Earth science and engineering with the King Abdullah University of Science and Technology (KAUST)

Ahmed Youssef Ragab Radwan

Visiting Student (former), Information Science Lab
Visiting student at the Information Science Lab, in the Electrical Engineering Department, CEMSE, King Abdullah University of Science and Technology (KAUST)

Carlos Hinojosa Montero

Postdoctoral Research Fellow, Image and Video Understanding Lab
Education and Early Career o Bachelor of System Engineering and Informatics, University: Universidad Industrial de Santander, 2011-2015. o Master of Science in Computer and System Engineering, University: Universidad Industrial de Santander, 2016-2018. o PhD in Computer Science, University: Universidad Industrial de Santander, 2017-2022.
<> artificial intelligence (20)

Najmeddine Dhieb

Yasmeen Alsaedy

M.S. Student, Computer Science
She is an AI researcher specializing in generative AI and deep learning. With a strong academic foundation and hands-on experience in machine learning, data science and artificial intelligence, she is passionate about advancing AI applications in real-world scenarios. She has contributed to cutting-edge projects, published research, and collaborated on innovative solutions that bridge the gap between AI theory and practice. Her expertise includes designing and implementing advanced data models, AI-driven visual/text computing, and deep learning architectures.

Yasser Jaber

Visiting Student Researcher ,Machine Learning Engineer at KAUST (King Abdullah University of Science and Technology).
Syed Abidullah Fareed

Syed Abidullah Fareed

Visiting Student (former), Information Science Lab

Ahmed Youssef Ragab Radwan

Visiting Student (former), Information Science Lab
Visiting student at the Information Science Lab, in the Electrical Engineering Department, CEMSE, King Abdullah University of Science and Technology (KAUST)

Efficient Localization of Human Actions and Moments in Videos

-

B3 L5 R5220

Abstract We are stumbling across a video tsunami flooding our communication channels. The ubiquity of digital cameras and social networks has increased the amount of visual media content generated and shared by people, in particular videos. Cisco reports that 82% of the internet traffic would be in the form of videos by 2022. The computer vision community has embraced this challenge by offering the first building blocks to translate the visual data in segmented video clips into semantic tags. However, users usually require to go beyond tagging at the video level. For example, someone may want

Computer vision: Teaching computers how to see the world

1 min read ·
Ghanem works in the Visual Computing Center (VCC) and is interested in computer vision, image processing, and machine learning.

Student Focus: Adel Bibi

1 min read ·
KAUST Ph.D. student Adel Bibi, who works on bridging the gap between theory and practice in deep learning, believes we're living in a very exciting time.

Testing the blind spots in artificial intelligence

1 min read ·
Understanding the situations when artificial intelligence can fail is critical for application of future autonomous vehicles and medical diagnostics.

ActivityNet is featured in the 2019 Artificial Intelligence Index

1 min read ·
ActivityNet is featured in the AI Index as the benchmark for the algorithms that can recognize human actions and activities from videos.

Prof. Bernard Ghanem to give a talk at Machines Can See 2021

1 min read ·
The fifth annual international summit ‘Machines Can See’ will host IVUL's own Prof. Bernard Ghanem as a speaker. The summit, to be held on July 8th 2021, is hosted by VisionLabs, a leading software company devoted to developing products based on state-of-the-art Computer Vision algorithms. The summit will be a space for Computer Vision and Machine Learning leading experts to discuss technology trends and share experience regarding human-centric technologies. Together with Prof. Bernard Ghanem, the summit will feature Professors Dima Damen, Efstratios Gavves, Ira Kemelmacher-Shlizerman, and

Seven IVUL members recognized as Outstanding Reviewers by CVPR 2021

1 min read ·
The 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) has granted Outstanding Reviewer awards to seven members of IVUL: Alejandro Pardo, Ali Thabet, Chen Zhao, Mattia Soldan, Mengmeng Xu, Juan C. Pérez, and Silvio Giancola. CVPR, a premier annual computer vision event that will take place virtually from June 19th to June 25th, is the largest computer vision conference in the world, gathering researchers from academia and industry alike. The peer-review process through which the conference determines acceptance of papers relies on expert reviewers from across the world

IVUL paper Wins Best Poster award at CVPR Workshop

1 min read ·
A paper by IVUL members won a Best Poster award at the LatinX in Computer Vision Workshop at CVPR 2021, the world-renowned venue for research in Computer Vision. The paper, "BAOD: Budget-Aware Object Detection", was written by four IVUL members, Alejandro Pardo, Mengmeng Frost Xu, Ali K. Thabet, and Bernard Ghanem, in collaboration with Professor Pablo Arbeláez, from Universidad de los Andes. The paper studies the efficiency with which object-detection systems learn when constrained by limited budgets. We congratulate the authors!

SDAIA, KAUST sign MoU to develop AI research and innovation in Saudi Arabia

1 min read ·
Saudi Gazette report JEDDAH — The Saudi Data and Artificial Intelligence Authority (SDAIA) and King Abdullah University of Science and Technology (KAUST) have signed a memorandum of understanding to unite efforts to develop Artificial Intelligence (AI) research and modern technologies in the Kingdom. The MoU was signed by the CEO of the National Center for Artificial Intelligence, the innovative arm of SDAIA, Dr. Majid Al-Tuwaijri, and by KAUST President, Professor Tony Chan, the Saudi Press Agency reported on Thursday. The MoU supports science and technology research and improves its quality

Victor Escorcia

Research Scientist committed to innovating AI agents to empower creativity and increase productivity. Passionate about developing cutting-edge AI applications involving video understanding and creative storytelling. I have a wide range of research and engineering interests from on-device AI to General AI. Reach out!

Silvio Giancola

Silvio Giancola is a Research Scientist at King Abdullah University of Science and Technology (KAUST), under the supervision of Prof. Bernard Ghanem in the Image and Video Understanding Laboratory (IVUL), part of the Center of Excellence for Generative AI (GenAI).

Frankly Toro

Frankly Toro is a Ms/Ph.D. student under the supervision of Prof. Bernard Ghanem at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST). Education and Early Career He is a graduate of National University of Colombia where he received a B.S. degree in Mechatronics. Education Profile B.S., Mechatronics , National University of Colombia, 2020

Carlos Hinojosa Montero

Postdoctoral Research Fellow, Image and Video Understanding Lab
Education and Early Career o Bachelor of System Engineering and Informatics, University: Universidad Industrial de Santander, 2011-2015. o Master of Science in Computer and System Engineering, University: Universidad Industrial de Santander, 2016-2018. o PhD in Computer Science, University: Universidad Industrial de Santander, 2017-2022.

Bernard Ghanem

Professor Ghanem's research focuses on computer vision and machine learning, emphasizing large-scale video understanding, vision for automated navigation and theoretical foundations.

Alejandro Pardo

Alejandro Pardo is a Ph.D. candidate in the Electrical and Computer Engineering (ECE) program under the supervision of Professor Bernard Ghanem at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) in Saudi Arabia. Education and Early Career Alejandro has an Engineer’s degree in Artificial Intelligence in both Electronics and Biomedical Engineering from the University of Los Andes in Colombia in 2017. He continued his studies at the University of Los Andes and received his Master’s Degree in Biomedical Engineering in 2018. He visited KAUST as a
<> UAV (7)

Mohammed Alwagait

Mohammed is a PhD Student in the Electrical and Computer Engineering program (ECE) at KAUST. He focuses on Reinforcement Learning Based Energy Saving Path Planning and Control for UAVs.

Sim-to-Real Transfer for Autonomous Navigation

-

B2 L5 R5220

This work investigates the problem of transfer from simulation to the real world in the context of autonomous navigation. To this end, we first present a photo-realistic training and evaluation simulator Sim4CV which enables several applications across various fields of computer vision. Built on top of the Unreal Engine, the simulator features cars and unmanned aerial vehicles (UAVs) with a realistic physics simulation and diverse urban and suburban 3D environments. We demonstrate the versatility of the simulator with two case studies: autonomous UAV-based tracking of moving objects and autonomous driving using supervised learning.

Computer vision: Teaching computers how to see the world

1 min read ·
Ghanem works in the Visual Computing Center (VCC) and is interested in computer vision, image processing, and machine learning.

Teaching algorithms to see

1 min read ·
Four hundred hours of video are uploaded to YouTube every minute. Other than using text to search the title, description or tags associated with a video, video content search is limited. In addition to helping users find content more quickly and accurately, the ability to search video content is of paramount importance to video platforms and advertisers. Last year, YouTube was embroiled in controversy after rolling video ads for Coca-Cola and Amazon, among others, were shown before racist and extremist content. Advertising content is a major revenue stream for video platforms like YouTube

KAUST Ph.D. student Matthias Mueller wins award for drone research

1 min read ·

UAV

KAUST Ph.D. student Matthias Mueller, who works in the Image and Video Understanding Lab under the supervision of KAUST Associate Professor Bernard Ghanem, won the Best Paper/Presentation Award at the 2nd International Workshop on Computer Vision for Unmanned Aerial Vehicles (UAVs). UAVs are commonly known as drones. The workshop was held in September 2018 in Germany in the post-proceedings of the 15th European Conference on Computer Vision workshops. Müller's paper entitled "Teaching UAVs to Race: End to End Regression of Agile Controls in Simulation" outlines the research of Müller and his

Beyond self-driving simulations: teaching machines to learn

1 min read ·
Teaching has the power to test the limits of one's knowledge. Teaching algorithms to learn using machine learning is making it possible for cars to do away with human drivers in the near future, but this has also opened up new questions about the limits of our knowledge of the brain and learning. Bernard Ghanem, KAUST associate professor of electrical engineering from the University's Visual Computing Center and principal investigator of the Image and Video Understanding Lab, applies machine learning techniques to computer vision for automated navigation (for example, self-driving cars and

Bernard Ghanem

Professor Ghanem's research focuses on computer vision and machine learning, emphasizing large-scale video understanding, vision for automated navigation and theoretical foundations.
<> CVPR (6) <> robotics (6)

Sim-to-Real Transfer for Autonomous Navigation

-

B2 L5 R5220

This work investigates the problem of transfer from simulation to the real world in the context of autonomous navigation. To this end, we first present a photo-realistic training and evaluation simulator Sim4CV which enables several applications across various fields of computer vision. Built on top of the Unreal Engine, the simulator features cars and unmanned aerial vehicles (UAVs) with a realistic physics simulation and diverse urban and suburban 3D environments. We demonstrate the versatility of the simulator with two case studies: autonomous UAV-based tracking of moving objects and autonomous driving using supervised learning.

Best Business Plan at VIEW 2016

1 min read ·
Hachid won the award for the Venture pitch with the best business plan at the Fifth Annual Vision Industry and Entrepreneur Workshop (VIEW) 2016.

Silvio Giancola

Silvio Giancola is a Research Scientist at King Abdullah University of Science and Technology (KAUST), under the supervision of Prof. Bernard Ghanem in the Image and Video Understanding Laboratory (IVUL), part of the Center of Excellence for Generative AI (GenAI).

Matthias Mueller

Matthias Mueller was an Electrical and Computer Engineering Ph.D. candidate in Image and Video Understanding Lab (IVUL) Group at Visual Computing Center (VCC) under the supervision of Prof. Bernard Ghanem at King Abdullah University of Science and Technology (KAUST). Education and Early Career Matthias graduated with a B.Sc. in Electrical Engineering and Math Minor from Texas A&M University in 2011. After graduation, he joined P+Z Engineering in Munich, Germany as an Electrical Engineer and worked for 3 years on the development of mild-hybrid electric machines at BMW. In 2014, he started his M

Lama Alssum

Ph.D. Student, Computer Science
Lama Alssum is a Ph.D. student in Computer Science under the supervision of Professor Bernard Ghanem in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Early Career Lama studied Information technology at King Saud University (KSU) in Riyadh and graduated with a Bachelor degree in 2011. After her bachelor degree, she joined KSU as a Teaching Assistant. Later on, she continued her studies and earned her Master degree in Computer Science from the School of Computing Science at the University of Glasgow, United Kingdom. Lama first joined

Frankly Toro

Frankly Toro is a Ms/Ph.D. student under the supervision of Prof. Bernard Ghanem at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST). Education and Early Career He is a graduate of National University of Colombia where he received a B.S. degree in Mechatronics. Education Profile B.S., Mechatronics , National University of Colombia, 2020
<> Video Understanding (6)

Fida Mohammad Thoker

Postdoctoral Research Fellow

ActivityNet is featured in the 2019 Artificial Intelligence Index

1 min read ·
ActivityNet is featured in the AI Index as the benchmark for the algorithms that can recognize human actions and activities from videos.

Victor Escorcia

Research Scientist committed to innovating AI agents to empower creativity and increase productivity. Passionate about developing cutting-edge AI applications involving video understanding and creative storytelling. I have a wide range of research and engineering interests from on-device AI to General AI. Reach out!

Mengmeng Xu (Frost)

Mengmeng Xu (Frost) was an Electrical and Computer Engineering PhD Student in Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. He is currently continuing his Ph.D. Education and Early Career Mengmeng obtained his bachelor's degree in Optics and Optical Sciences from Zhejiang University in China in 2017 and his Master's Degree from KAUST under the supervision of Professor Bernard Ghanem. Research Interests He is mainly focusing on problems that arise in computer vision, including

Chen Zhao

Chen Zhao is a Research Scientist at KAUST, and Lead of the Video Understanding Theme in the Image and Video Understanding Lab. She received her Ph.D. degree from Peking University, China in 2016. She studied in University of Washington, US from 2012 to 2013, and at the National Institute of Informatics, Japan in 2016. She has published 40+ papers on representative journals and conferences such as TPAMI, CVPR, ICCV, ECCV, and has received over 3000 citations according to Google Scholar.

Carlos Hinojosa Montero

Postdoctoral Research Fellow, Image and Video Understanding Lab
Education and Early Career o Bachelor of System Engineering and Informatics, University: Universidad Industrial de Santander, 2011-2015. o Master of Science in Computer and System Engineering, University: Universidad Industrial de Santander, 2016-2018. o PhD in Computer Science, University: Universidad Industrial de Santander, 2017-2022.
<> optimization (5)

Ahmed Youssef Ragab Radwan

Visiting Student (former), Information Science Lab
Visiting student at the Information Science Lab, in the Electrical Engineering Department, CEMSE, King Abdullah University of Science and Technology (KAUST)

Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives

-

KAUST

In this dissertation, we aim at theoretically studying and analyzing deep learning models. Since deep models substantially vary in their shapes and sizes, in this dissertation, we restrict our work to a single fundamental block of layers that is common in almost all architectures. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation function and then lastly followed by another affine layer. We study this block of layers from three different perspectives. (i) An Optimization Perspective. We try addressing the following question: Is it possible that the output of the forward pass through the block of layers highlighted above is an optimal solution to a certain convex optimization problem? As a result, we show an equivalency between the forward pass through this block of layers and a single iteration of certain types of deterministic and stochastic algorithms solving a particular class of tensor formulated convex optimization problems.

Aerial Path Planning for Urban Scene Reconstruction: A Continuous Optimization Method and Benchmark

1 min read ·
Small unmanned aerial vehicles (UAVs) are ideal capturing devices for high-resolution urban 3D reconstructions using multi-view stereo. Nevertheless, practical considerations such as safety usually mean that access to the scan target is often only available for a short amount of time, especially in urban environments. It, therefore, becomes crucial to perform both view and path planning to minimize flight time while ensuring complete and accurate reconstructions. In this work, we address the challenge of automatic view and path planning for UAV-based aerial imaging with the goal of urban

Adel is invited to give a talk in EECVC on "Optimization meets Deep Learning"

1 min read ·
​Adel is invited to give a talk in EECVC on "Optimization meets Deep Learning"​. It is a 45 minutes talk scheduled on the 6th of July 2019.

Adel Bibi

Adel Bibi is a postdoctoral research assistant in computer vision and machine learning at the Torr Vision Group working with Professor Philip Torr at the University of Oxford. Prior to that, he received his MSc and PhD degrees from King Abdullah University of Science & Technology (KAUST) where he was part of the Image and Video Understanding Lab (IVUL) advised by Professor Bernard Ghanem. Education and Early Career Adel Bibi has a Bachelor’s Degree in Electrical Engineering from Kuwait University in 2014. He received his Master Degree in Electrical Engineering from King Abdullah University of
<> Signal processing (4) <> 3D object detection (3)

Indoor 3D Scene Understanding Using Depth Sensors

-

KAUST

One of the main goals in computer vision is to achieve a human-like understanding of images. This understanding has been recently represented in various forms, including image classification, object detection, semantic segmentation, among many others. Nevertheless, image understanding has been mainly studied in the 2D image frame, so more information is needed to relate them to the 3D world. With the emergence of 3D sensors (e.g. the Microsoft Kinect), which provide depth along with color information, the task of propagating 2D knowledge into 3D becomes more attainable and enables interaction between a machine (e.g. robot) and its environment. This dissertation focuses on three aspects of indoor 3D scene understanding: (1) 2D-driven 3D object detection for single frame scenes with inherent 2D information, (2) 3D object instance segmentation for 3D reconstructed scenes, and (3) using room and floor orientation for automatic labeling of indoor scenes that could be used for self-supervised object segmentation. These methods allow capturing of physical extents of 3D objects, such as their sizes and actual locations within a scene.

IVUL gets 3 papers accepted to ICCV 2017

1 min read ·
​​IVUL got 3 papers accepted to ICCV 2017! These papers address research problems in convolutional sparse coding, line drawing analysis, and 3D object detection.​​​

Jean Lahoud

Jean Lahoud was a Ph. D. student in Image and Video Understanding Lab (IVUL) Group under the supervision of Prof. Bernard Ghanem at KAUST. Education and Early Career Jean Lahoud received his Bachelor of Engineering in Mechanical Engineering from Notre Dame University in Lebanon in 2012. In 2014, he obtained his Master of Engineering degree in the same field from American University of Beirut in Lebanon. Before joining KAUST, Jean was a product manager at Murex systems in Lebanon. Research Interest Jean Lahoud is interested in 3​D scene understanding using RGB-D sensors. Honors and Awards In
<> AI (3) <> ICCV (3) <> image processing (3)

Sara Rojas Martinez

Sara Rojas Martinez is a Ph.D. student in the KAUST Image and Video Understanding Lab (IVUL) under the supervision of Professor Bernard Ghanem. Before joining KAUST, Sara obtained a master’s degree in Biomedical Engineering from Universidad de Los Andes, Bogotá, Colombia. Research Interests Sara is interested in topics related to the investigation in Artificial Intelligence and Computer Vision. . Education Profile • M.S., Biomedical Engineering, University of Los Andes, Colombia, 2018 • B.E., Artificial Intelligence in Electronics Engineering, University of Los Andes, Colombia, 2017

Sara Shaheen

Sara Shaheen was a Ph.D. student in Computer Science under the supervision of Professor Bernard Ghanem at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST). She is currently an Assistant Professor in Computer Science at Prince Sultan University (PSU) in Riyadh, Saudi Arabia. Education and Career Sara received her Bachelor degree in Computer Science from Prince Sultan University (PSU) in Riyadh in 2010. She joined the MS/PhD program in KAUST and earned her Master and Ph.D. in Computer Science in 2017. She was a part of Image and Video Understanding

Alejandro Pardo

Alejandro Pardo is a Ph.D. candidate in the Electrical and Computer Engineering (ECE) program under the supervision of Professor Bernard Ghanem at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) in Saudi Arabia. Education and Early Career Alejandro has an Engineer’s degree in Artificial Intelligence in both Electronics and Biomedical Engineering from the University of Los Andes in Colombia in 2017. He continued his studies at the University of Los Andes and received his Master’s Degree in Biomedical Engineering in 2018. He visited KAUST as a
<> MATLAB (3) <> AI4Science (2) <> algorithm (2) <> Compressive Sensing (2) <> computer graphics (2) <> Continual Learning (2) <> data science (2) <> Deep generative models (2) <> ECCV (2) <> Generative AI and LLMs (2) <> healthcare (2) <> Human Activity Recognition (2) <> ICVSS (2) <> IoT (2) <> Localization (2) <> Network Design (2) <> point cloud (2) <> Programming language (2) <> Reinforcement Learning (2) <> semantic analysis (2) <> stroke authorship recognition (2) <> three paper accepted (2) <> visual computing (2) <> 3D understanding (1) <> 5G networks (1) <> 6g wireless systems (1) <> Action Recognition (1) <> Action Recognition Challenge (1) <> Action understanding (1) <> adaptive control (1) <> Aerial Robotics (1) <> AI for healthcare (1) <> analysis of contextual information (1) <> applied mathematics (1) <> AR development (1) <> asynchronous algorithms (1) <> beamforming (1) <> big data (1) <> biomechanics (1) <> Biomedical Signal Processing (1) <> bioscience (1) <> biotechnology (1) <> BLE communication (1) <> calculus of variations (1) <> Cellular Networks (1) <> CGF 2015 (1) <> cloud- and fog-radio access networks (1) <> communication (1) <> communication networks (1) <> communication systems (1) <> Compressed Sensing Approach (1) <> computational methods (1) <> computer networks (1) <> convolutional sparse coding (1) <> Cooperative networks (1) <> cross-layer optimization (1) <> cybersecurity (1) <> data analysis (1) <> Data Analyst (1) <> Dead Sea Jordan (1) <> deep neural networks (1) <> dense captioning (1) <> detecting fraudulent sketches (1) <> development (1) <> Digital Communications (1) <> Digital signal processing (1) <> Driving Policy Transfer (1) <> Dynamical Systems (1) <> EECVC (1) <> Efficient Machine Learning (1) <> electrical engineering (1) <> Electron Transport (1) <> embedded systems (1) <> Embedded systems. (1) <> energy efficiency (1) <> ePoster Competition (1) <> eurographics (1) <> fellowship (1) <> five papers accepted (1) <> fluid dynamics (1) <> Forbes ME (1) <> free boundary problems (1) <> generative adversarial network (1) <> global UNESCO event (1) <> GPU Computing (1) <> GPU Technology Conference (1)