Steven McDonagh

papers

510

total citations

papers (11)

Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping

ECCV 2020arXiv

citations

Long-Tail Recognition via Compositional Knowledge Transfer

CVPR 2022arXiv

citations

MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation

CVPR 2024arXiv

citations

CroMo: Cross-Modal Learning for Monocular Depth Estimation

CVPR 2022arXiv

citations

Learning To Name Classes for Vision and Language Models

CVPR 2023arXiv

citations

Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection

ECCV 2020arXiv

citations

Multi-task Learning with 3D-Aware Regularization

ICLR 2024arXiv

citations

Tunable Convolutions With Parametric Multi-Loss Optimization

CVPR 2023arXiv

citations

Steven McDonagh

papers (11)

DeepLPF: Deep Local Parametric Filters for Image Enhancement

A Multi-Hypothesis Approach to Color Constancy

On the Out-of-distribution Generalization of Probabilistic Image Modelling

Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping

Long-Tail Recognition via Compositional Knowledge Transfer

MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation

CroMo: Cross-Modal Learning for Monocular Depth Estimation

Learning To Name Classes for Vision and Language Models

Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection

Multi-task Learning with 3D-Aware Regularization

Tunable Convolutions With Parametric Multi-Loss Optimization

papers (11)

DeepLPF: Deep Local Parametric Filters for Image Enhancement

A Multi-Hypothesis Approach to Color Constancy

On the Out-of-distribution Generalization of Probabilistic Image Modelling

Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping

Long-Tail Recognition via Compositional Knowledge Transfer

MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation

CroMo: Cross-Modal Learning for Monocular Depth Estimation

Learning To Name Classes for Vision and Language Models

Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection

Multi-task Learning with 3D-Aware Regularization

Tunable Convolutions With Parametric Multi-Loss Optimization