Benjamin Missaoui

Benjamin Missaoui

Computer Science Master’s student

Georgia Institute of Technology

Biography

Hi! I’m Benjamin, glad you found my website! I’m currently a PhD Student at Nvidia’s Dynamic Vision and Learning lab supervised by Laura Leal-Taixé. My research interests include Video Understanding, Self-Supervised Learning and Multi-Object Tracking. Check out our lab here! Before that, I graduated from Georgia Tech with a CS Master’s in May 2024. I’m also a piano and travel enthusiast! Don’t hesitate to reach out :)

Download my resumé

Interests
  • Video Understanding
  • Self-Supervised Learning
  • Multi-Object Tracking
Education
  • MSc in Computer Science, ML, 2023-2024

    Georgia Tech, USA

  • MEng in Computer Science, 2018-2023

    University of Technology of Compiègne, France

Experience

 
 
 
 
 
Nvidia
PhD Student, Video Understanding
Jul 2024 – Present Modena, Italy
Online Multi-Object Tracking with Graph Neural Networks under Dr. Laura Leal-Taixé.
 
 
 
 
 
Bosch Research
AI Research Intern, Foundation Models
Jun 2023 – Dec 2023 Singapore, Singapore

6-month research internship on contrastive learning for images. Here, my work has focused on using foundation models (like SAM) to select better views for contrastive learning (which is usually done randomly). Accepted at NeurIPS 2023 workshop [1]. I also invented a method for batch image annotation (pending patent) [2].

[1] B. Missaoui, C. Yuan, “SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling” (Accepted at NeurIPS'23 workshop)

[2] T. Ngo, B. Missaoui et al., Automated Image Annotation Method And System (EU patent)

 
 
 
 
 
Georgia Tech
Research project, 3D Computer Vision
Jan 2023 – May 2024 Atlanta, USA

Research project on 3D reconstruction with Neural Radiance Fields (NeRFs), which we extended to be able to generate any wavelength (not just RGB). This enables all new use cases in biology and recycling, where different plants or materials exhibit different properties depending on the wavelength they are viewed from. Under review at 3DV 2025[4].

[3] G. Chen, H. Muriki, B. Missaoui, al., “HS-NeRF: HyperSpectral Neural Radiance Fields with Continuous Radiance and Transparency Spectra” (Under review at 3DV 2025)

 
 
 
 
 
CNRS
Research assistant, Autonomous vehicles
Sep 2022 – Jan 2023 Compiègne, France

Developed a solution fusing camera, LiDAR and IMU for projecting landmarks from 2D maps to the vehicle’s camera frame, enabling to get high-quality-pseudo labeled training data for object detection models.

The method was accepted at IEEE IV 2023 [5], the most prestigious conference on intelligent vehicles.

[4] B. Missaoui, M. Noizet, P. Xu, “Map-aided annotation for pole base detection” (Accepted at IV 2023)

 
 
 
 
 
Scortex
Research Engineer Intern, Computer Vision
Jul 2021 – Jan 2022 Paris, France

6 months research internship on Deep Unsupervised Anomaly Detection. Goal: Improve defect detection on industrial parts.

  • Co-authored a heuristic to remove defective parts in a fully unlabelled dataset with 90+ AUC.
  • Fine-tuned pre-trained networks with synthetic defects to improve defect detection AUC from 91.6 to 96.1 points.

Publications

Quickly discover relevant content by filtering publications.
(2023). SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling. Accepted at NeurIPS 2023 workshop.

PDF

(2023). Map-aided annotation for pole base detection. Accepted at IEEE IV 2023.

PDF

(2022). Data refinement for fully unsupervised visual inspection using pre-trained networks.

PDF