Serena Yeung

papers

1,223

total citations

papers (17)

Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

NEURIPS 2022arXiv

624

citations

Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision

CVPR 2021arXiv

citations

Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations

NEURIPS 2021arXiv

citations

DARCNN: Domain Adaptive Region-Based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical Images

CVPR 2021arXiv

citations

BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

CVPR 2025arXiv

citations

Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation

CVPR 2025arXiv

citations

LOVM: Language-Only Vision Model Selection

NEURIPS 2023arXiv

citations

MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research

CVPR 2025arXiv

citations

Generalizable Neural Fields as Partially Observed Neural Processes

ICCV 2023arXiv

citations

INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms

NEURIPS 2023

citations

NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action

CVPR 2023

citations

GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition

ICCV 2021

citations

Serena Yeung

papers (17)

Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

DataPerf: Benchmarks for Data-Centric AI Development

PROB: Probabilistic Objectness for Open World Object Detection

Holistic 3D Human and Scene Mesh Estimation From Single View Images

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Describing Differences in Image Sets with Natural Language

Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision

Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations

DARCNN: Domain Adaptive Region-Based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical Images

BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation

LOVM: Language-Only Vision Model Selection

MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research

Generalizable Neural Fields as Partially Observed Neural Processes

INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms

NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action

GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition

papers (17)

Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

DataPerf: Benchmarks for Data-Centric AI Development

PROB: Probabilistic Objectness for Open World Object Detection

Holistic 3D Human and Scene Mesh Estimation From Single View Images

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Describing Differences in Image Sets with Natural Language

Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision

Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations

DARCNN: Domain Adaptive Region-Based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical Images

BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation

LOVM: Language-Only Vision Model Selection

MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research

Generalizable Neural Fields as Partially Observed Neural Processes

INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms

NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action

GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition