Alexander Moore
I’m documenting my independent research into computer vision for autonomous vehicles — follow along on the blog or see my Google Scholar for publications.
I am an AI Research Scientist at Lawrence Livermore National Laboratory, working on computer vision for video understanding — video object segmentation, multi-object tracking (MOT), and amodal scene completion. My research spans foundation model fine-tuning, transferrable representation learning, and real-world video perception. Independently, I’m building toward end-to-end autonomous driving from natural video: see feature extraction from multi-camera video and E2E driving.
Select Publications
- NovisVQ: A Streaming Convolutional Neural Network for No-Reference Opinion-Unaware Frame Quality Assessment
- Streaming, lightweight, no-reference video quality assessment.
- Training for X-Ray Vision: MOVi-MC-AC
- First-ever dataset with ground-truth amodal content for occluded objects in cluttered video.
- An Analysis of Segment Anything 2
- Probing weaknesses of state-of-the-art video object segmentation for obscured object tracking.
- Addressing Issues with Working Memory in Video Object Segmentation
- Modifying the working memory buffer in VOS models (SAM2, XMem, Cutie) to improve tracking during intermission periods.
- ChemVise: Maximizing Out-of-Distribution Chemical Detection with Zero-Shot Learning
- ICMLA 2023 — Oral presentation
- ACGANs Improve Chemical Sensors for Challenging Distributions
- ICMLA 2022 — Oral presentation
- Cycles Improve Conditional Generators
- ADMA 2022
- ChemTime: Rapid and Early Classification of Chemical Sensor Time Series
- Preprint 2023
- Identifying Struggling Students by Comparing Online Tutor Clickstreams
- AIED 2021
- Identifying Explanations Within Student-Tutor Chatlogs
- EDM 2022
- CASIS LLNL 2024 — Vision-Language LLMs From Scratch Tutorial & Computational Objectness from Motion in Video Poster
- Stanford ICME Transformers & LLMs Workshop
Education
- Worcester Polytechnic Institute — Ph.D. & M.S. Data Science, 2019–2023. 4.0 GPA. Presidential Fellowship ($90k/yr)
- Reed College — B.A. Mathematics & Statistics, 2016–2019. Presidential Commendation, Dean’s List