Jihao Liu

Affiliations

CUHK, MMLab

papers

378

total citations

papers (10)

Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images

CVPR 2020arXiv

114

citations

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers

ECCV 2022arXiv

citations

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

CVPR 2023arXiv

citations

Learning Where to Focus for Efficient Video Object Detection

ECCV 2020arXiv

citations

GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding

ICCV 2023arXiv

citations

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

ICML 2024arXiv

citations

Jihao Liu

Affiliations

papers (10)

Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

Learning Where to Focus for Efficient Video Object Detection

GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

GLID: Pre-training a Generalist Encoder-Decoder Vision Model

EasyDrag: Efficient Point-based Manipulation on Diffusion Models

Enhancing Vision-Language Model with Unmasked Token Alignment

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

papers (10)

Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

Learning Where to Focus for Efficient Video Object Detection

GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

GLID: Pre-training a Generalist Encoder-Decoder Vision Model

EasyDrag: Efficient Point-based Manipulation on Diffusion Models

Enhancing Vision-Language Model with Unmasked Token Alignment

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"