Long Mai

papers

888

total citations

papers (11)

Learning To Recover 3D Scene Shape From a Single Image

CVPR 2021arXiv

299

citations

BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

NEURIPS 2020arXiv

245

citations

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

CVPR 2021arXiv

211

citations

Active Speakers in Context

CVPR 2020arXiv

citations

Context-Aware Group Captioning via Self-Attention and Contrastive Features

CVPR 2020arXiv

citations

GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting

ICCV 2025arXiv

citations

Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces

ICCV 2025arXiv

citations

TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models

ICCV 2025arXiv

citations

Long Mai

papers (11)

Learning To Recover 3D Scene Shape From a Single Image

BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

Active Speakers in Context

Context-Aware Group Captioning via Self-Attention and Contrastive Features

GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting

Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces

TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models

REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder

Motion-Adjustable Neural Implicit Video Representation

Structure-Guided Ranking Loss for Single Image Depth Prediction

papers (11)

Learning To Recover 3D Scene Shape From a Single Image

BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

Active Speakers in Context

Context-Aware Group Captioning via Self-Attention and Contrastive Features

GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting

Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces

TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models

REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder

Motion-Adjustable Neural Implicit Video Representation

Structure-Guided Ranking Loss for Single Image Depth Prediction