Ross Girshick

papers

41,662

total citations

papers (14)

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

CVPR 2025arXiv

111

citations

Fast and Accurate Model Scaling

CVPR 2021arXiv

108

citations

A Multigrid Method for Efficiently Training Video Models

CVPR 2020arXiv

citations

The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining

ICCV 2023arXiv

citations

Are Labels Necessary for Neural Architecture Search?

ECCV 2020arXiv

citations

Ross Girshick

papers (14)

Momentum Contrast for Unsupervised Visual Representation Learning

Segment Anything

Masked Autoencoders Are Scalable Vision Learners

Designing Network Design Spaces

Exploring Plain Vision Transformer Backbones for Object Detection

PointRend: Image Segmentation As Rendering

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Fast and Accurate Model Scaling

A Multigrid Method for Efficiently Training Video Models

The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining

Are Labels Necessary for Neural Architecture Search?

papers (14)

Momentum Contrast for Unsupervised Visual Representation Learning

Segment Anything

Masked Autoencoders Are Scalable Vision Learners

Designing Network Design Spaces

Exploring Plain Vision Transformer Backbones for Object Detection

PointRend: Image Segmentation As Rendering

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Fast and Accurate Model Scaling

A Multigrid Method for Efficiently Training Video Models

The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining

Are Labels Necessary for Neural Architecture Search?