Bryan Plummer

About

Bryan Plummer is an Assistant Professor in the Department of Computer Science at Boston University. He previously worked at Boston University as a Postdoctoral Associate and Research Assistant Professor, and is a member of the IVC Group. He obtained his PhD in the computer vision group at the University of Illinois at Urbana-Champaign. His research interests fall within the umbrella of artificial intelligence, with a focus on visual recognition, scene understanding, interpretable machine learning, and understanding the relationship between vision and language.

Research topics

• Artificial Intelligence
• Natural Language Processing
• Computer Science
• Machine Learning
• Theoretical computer science
• Cognitive psychology
• Psychology

Selected publications

• LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval

  2021 · 75 citations

  Senior authorCorresponding

  The goal of weakly-supervised video moment retrieval is to localize the video segment most relevant to a description without access to temporal annotations during training. Prior work uses co-attention mechanisms to understand relationships between the vision and language data, but they lack contextual information between video frames that can be useful to determine how well a segment relates to the query. To address this, we propose an efficient Latent Graph Co-Attention Network (LoGAN) that ex…

  DOI

• MULE: Multimodal Universal Language Embedding

  Proceedings of the AAAI Conference on Artificial Intelligence · 2020 · 39 citations

  Senior authorCorresponding

  Existing vision-language methods typically support two languages at a time at most. In this paper, we present a modular approach which can easily be incorporated into existing vision-language methods in order to support many languages. We accomplish this by learning a single shared Multimodal Universal Language Embedding (MULE) which has been visually-semantically aligned across all languages. Then we learn to relate MULE to visual data as if it were a single language. Our method is not architec…

  DOI

• ERM++: An Improved Baseline for Domain Generalization

  2025-02-26 · 8 citations

  articleSenior author

  Domain Generalization (DG) aims to develop classifiers that can generalize to new, unseen data distributions, a critical capability when collecting new domain-specific data is impractical. A common DG baseline minimizes the empirical risk on the source domains. Recent studies have shown that this approach, known as Empirical Risk Minimization (ERM), can outperform most more complex DG methods when properly tuned. However, these studies have primarily focused on a narrow set of hyperparameters, n…

  PublisherDOI

• Anatomy‐Guided, Modality‐Agnostic Segmentation of Neuroimaging Abnormalities

  Human Brain Mapping · 2025-09-16 · 2 citations

  articleOpen access

  Magnetic resonance imaging (MRI) offers multiple sequences that provide complementary views of brain anatomy and pathology. However, real-world datasets often exhibit variability in sequence availability due to clinical and logistical constraints. This variability complicates radiological interpretation and limits the generalizability of machine learning models that depend on a consistent multimodal input. Here, we propose an anatomy-guided, modality-agnostic framework to assess disease-related…

  PublisherOA PDFDOI

• Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling

  2025-06-10 · 1 citations

  articleSenior author

  Given an isolated garment image in a canonical product view and a separate image of a person, the virtual try-on task aims to generate a new image of the person wearing the target garment. Prior virtual try-on works face two major challenges in achieving this goal: a) the paired (human, garment) training data has limited availability; b) generating textures on the human that perfectly match that of the prompted garment is difficult, often resulting in distorted text and faded textures. Our work…

  PublisherDOI

Recent grants

• Collaborative Research: Image-based Readouts of Cellular State using Universal Morphology Embeddings

  NSF · $499k · 2022–2025

Frequent coauthors

• Kate Saenko

  70 shared

• Reuben Tan

  21 shared

• Svetlana Lazebnik

  20 shared

• Stan Sclaroff

  Boston University

  18 shared

• Andrea Burns

  17 shared

• Donghyun Kim

  14 shared

• Ranjitha Kumar

  University of Illinois Urbana-Champaign

  12 shared

• Piotr Teterwak

  10 shared

Labs

• Data Mining & Data ManagementPI

Similar researchers at Boston University

• Ran Canettih-78