Biography

I am a Principal Machine Learning Scientist at Intelmatix. I received my PhD and MSc degrees in Computer Science (specializing in Computer Vision and Machine Learning) from KAUST. I was part of the Image and Video Understanding Lab (IVUL) advised by Bernard Ghanem. I received my undergraduate degree in both Computer Science and Mathematics from Cornell University. Prior to my current position, I worked at several leading technology companies, including DeepMind, Meta AI, AWS, and Amazon. My research interests include video understanding, multimodal representation learning, and computer vision and machine learning in general.

Interests

  • Multimodal representation learning
  • Video understanding
  • Computer Vision, Machine Learning, and Artificial Intelligence

Education

News

2023

[2023-02-01] Joined Intelmatix in Riyadh as a Principal Machine Learning Scientist.
[2023-01-23] Successfully defended my PhD dissertation.
[2023-01-01] Our recent work on using AI for fluid dynamics applications (in collaboration with the Mechanical Department at KAUST) is published in the Artificial Intelligence for the Earth Systems Journal.

Earlier News [Click to expand]

2022

Click to expand

[2022-12-02] Got married to the love of my life, Fadhilah Alduraiei.
[2022-09-23] Finished my internship at DeepMind.
[2022-06-23] Awarded the 2022 KAUST Academic Excellence Award for my PhD studies.
[2022-05-09] Started a Research Scientist Internship at DeepMind in London working with João Carreira.

2021

Click to expand

[2021-12-07] Successfully defended my PhD dissertation proposal and became a PhD candidate (previously a PhD student).
[2021-10-17] Presented my TSP work in ICCV 2021 at the CVEU workshop as a spotlight presentation.
[2021-10-05] Finished my internship at AWS.
[2021-08-17] TSP accepted to the ICCV 2021 Workshop on AI for Creative Video Editing and Understanding as a spotlight presentation.
[2021-07-05] Started an applied science internship at Amazon Web Services (AWS) in London. I’ll be working with the Machine Learning Solution Lab (MLSL).
[2021-01-05] Awarded the CEMSE Student Research Excellence Award for my PhD research work.

2020

Click to expand

[2020-12-08] Presented my XDC work in NeurIPS 2020 as a spotlight presentation.
[2020-11-23] My latest work, TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks, is on arXiv.
[2020-11-02] RefineLoc accepted to WACV 2021.
[2020-09-26] XDC accepted to NeurIPS 2020 as a spotlight presentation.
[2020-04-05] MortonNet accepted to the Visual Learning with Limited Labels workshop in CVPR 2020.
[2020-01-14] Appeared on a TV interview with MBC1’s Shabab Hub show to talk about my research and the computer vision field in general. The interview is in Arabic.

2019

Click to expand

[2019-12-02] My recent project with Meta AI on Self-Supervised Learning by Cross-Modal Audio-Video Clustering is on arXiv.
[2019-09-20] Finished my internship at Meta AI.
[2019-06-17] Attended CVPR19 and co-organized the 4th annual International Challenge on Activity Recognition (ActivityNet).
[2019-06-03] Started my research internship at Meta AI in Menlo Park, CA with Du Tran. I’ll be working on self-supervised representation learning for video.
[2019-03-30] My work on weakly-supervised action localization, RefineLoc, is on arXiv.
[2019-03-30] My recent project on self-supervision for point clouds, MortonNet, is on arXiv. Code is available on GitHub.

2018

Click to expand

[2018-09-15] Attended ECCV 2018 in Munich, Germany and presented our two accepted papers.
[2018-07-03] 2 papers (Action Search and DETAD) accepted to ECCV 2018.
[2018-07-14] Attended ICVSS 2018 summer school in Sicily.
[2018-06-22] Presented our DETAD work in the ActivityNet challenge workshop in CVPR18 (slides) and also released the code for the DETAD diagnosis tool.
[2018-06-01] I’ll attend CVPR18. Come check out our ActivityNet challenge workshop on Friday, June 22.
[2018-05-01] Started my PhD studies with Bernard Ghanem at KAUST. I’m continuing in the same research direction of video understanding and computer vision in general.
[2018-04-16] Got accepted to the ICVSS 2018 summer school in Sicily.
[2018-04-10] Successfully defended my Master’s thesis.
[2018-03-23] I’m co-organizing the third annual ActivityNet challenge in CVPR18, Salt Lake City (the challenge starts today). Check out our website. This year we have six exciting tasks and five novel action datasets.

2017

Click to expand

[2017-12-15] Graduated with an MSc in Computer Science from KAUST.
[2017-05-01] I’m co-organizing the second annual ActivityNet challenge in CVPR17, Hawaii (the challenge starts today).

2016

Click to expand

[2016-09-21] Started my Master’s degree in Computer Science at KAUST. I joined the multicultural and diverse Image and Video Understanding Lab (IVUL) advised by Bernard Ghanem.
[2016-06-06] Started a software development engineer internship at Amazon Corporate LLC, Seattle, WA with the Vendor Self Service, Business Advisor team.
[2016-05-29] Graduated from Cornell University with a Bachelors degree in both Computer Science and Mathematics.

Professional Experience

Intelmatix, Riyadh, Saudi Arabia [2023-Present]

Principal Machine Learning Scientist
Intelmatix is a deep tech AI company founded by a group of MIT technologists with a global presence through offices in Riyadh, London, and Boston. It provides organizations with Decision Intelligence technologies through custom AI solutions and Enterprise AI products that provide actionable insights and a competitive advantage in the AI era.

DeepMind (Google), London, UK [2022]

Research Scientist Intern
Team: Vision, DeepMind. Manager/Mentor: João Carreira.

Amazon Web Services (AWS), London, UK [2021]

Applied Science Intern
Team: Machine Learning Solutions Lab (MLSL), AWS. Manager: Clive Davies.

Meta AI, Menlo Park, CA [2019]

Research Intern
Team: Computer Vision, Meta AI. Manager/Mentor: Du Tran.
My research project was on Self-Supervised Representation Learning by Cross-Modal Audio-Video Clustering (project page). To the best of our knowledge, our work is the first method to demonstrate that self-supervision outperforms large-scale full-supervision in representation learning for action recognition.

Mantis Company [2017-2021]

Co-founder and Computer Vision Researcher
A state-of- the-art activity-based, advertising-centric automated video understanding platform. Mantis utilizes faster-than- real-time activity and object detection techniques for a fine-grained video content categorization to achieve a content-aware ads placement on videos.

Amazon Corporate LLC, Seattle, WA [2016]

Software Development Engineer Intern
Team: Vendor Self Service, Business Advisor. Manager: Ram Yerramilli.

Featured Publications

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed …
Preprint PDF Code Slides Video Supplementary Material

RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization

Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an …
Preprint PDF Code Video Supplementary Material

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

Visual and audio modalities are highly correlated, yet they contain different information. Their strong correlation makes it possible …
Preprint PDF Poster Slides Video Code (Pretrained Models) Supplementary Material

Self-Supervised Learning of Local Features in 3D Point Clouds

We present a self-supervised task on point clouds, in order to learn meaningful point-wise features that encode local structure around …
Preprint PDF Code

Action Search: Spotting Targets in Videos and Its Application to Temporal Action Localization

State-of-the-art temporal action detectors inefficiently search the entire video for specific actions. Despite the encouraging progress …
Preprint PDF Poster Slides Video Supplementary Material Human Searches Dataset + Code

DETAD: Diagnosing Error in Temporal Action Detectors

Despite the recent progress in video understanding and the continuous rate of improvement in temporal action localization throughout …
Preprint PDF Code Poster Slides Video Supplementary Material

Publications

Humam Alwassel, Silvio Giancola, Bernard Ghanem . TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks. In ICCVW [spotlight], 2021.

Preprint PDF Code Slides Video Supplementary Material

Alejandro Pardo, Humam Alwassel, Fabian Caba Heilbron, Ali Thabet, Bernard Ghanem . RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization. In WACV, 2021.

Preprint PDF Code Video Supplementary Material

Humam Alwassel, Dhruv Mahajan, Bruno Korbar, Lorenzo Torresani, Bernard Ghanem, Du Tran . Self-Supervised Learning by Cross-Modal Audio-Video Clustering. In NeurIPS [spotlight], 2020.

Preprint PDF Poster Slides Video Code (Pretrained Models) Supplementary Material

Ali Thabet, Humam Alwassel, Bernard Ghanem . Self-Supervised Learning of Local Features in 3D Point Clouds. In CVPRW, 2020.

Preprint PDF Code

Humam Alwassel, Fabian Caba Heilbron, Bernard Ghanem . Action Search: Spotting Targets in Videos and Its Application to Temporal Action Localization. In ECCV, 2018.

Preprint PDF Poster Slides Video Supplementary Material Human Searches Dataset + Code

See all publications

Miscellaneous

Academic Experience

International Challenge on Activity Recognition (ActivityNet) [2017-2022]

Co-organizer and Program Chair
Previously known as The ActivityNet Large Scale Activity Recognition Challenge. This annual challenge was held at CVPR and focused on the recognition of daily life, high-level, goal-oriented activities from user-generated videos typically found on the Internet video portals. It attracted a large number of participants from across the world and was sponsored by several industrial partners including Google DeepMind, Facebook AI, Google AI, Qualcomm, and Panasonic. Challenge pages: 2016, 2017, 2018, 2019, 2020, 2021, 2022.

Academic Reviewer for Top-Tier Computer Vision Venues [2018-Present]

Served as a reviewer and emergency reviewer for CVPR, ICCV, ECCV, NeurIPS, WACV, and BMVC.

Graduate Teaching Assistant

Honors and Awards

KAUST Academic Excellence Award [2022]

CEMSE Student Research Excellence Award [2021]

The annual CEMSE award is presented in recognition of the academic accomplishments and research impact created by CEMSE students in the fields of Applied Mathematics and Computer Science, Computer Science, Electrical and Computer Engineering, and Statistics.

KAUST Fellowship for MS and PhD Studies [2016-Present]

A fellowship which supports students for the duration of their graduate studies at KAUST. It includes ​full tuition support, monthly living allowance, housing, and medical coverage.

SACM Undergraduate Scholarship [2010-2016]

A scholarship awarded by the Saudi Arabian Cultural Mission to the United States. It covers the full tuition for an undergraduate STEM degree at a US university.

KAUST Gifted Student Program (KGSP) Scholarship [2010-2016]

KGSP is a prestigious scholarship awarded by KAUST to a select group of Saudi students, allowing them to pursue undergraduate degrees in STEM fields in the US, and then complete their master’s degree at KAUST.

Media Coverage

Shabab Hub Show [2020]: Appeared on a TV interview with MBC1’s Shabab Hub show to talk about my research and the computer vision field in general. The interview is in Arabic.

The Beacon Magazine [2019]: Appeared on the cover of the Winter 2019 issue.

KAUST News [2018]: Featured in a news article about our recent work in IVUL.

Contact

  • +966 55 170 8480
  • 4700 KAUST, Al Khawarizmi Building (Bldg 1), Office #2106-WS06, Thuwal, 23955-6900