Haoqi Fan

papers

19,142

total citations

papers (18)

Momentum Contrast for Unsupervised Visual Representation Learning

CVPR 2020arXiv

14,222

citations

Multiscale Vision Transformers

ICCV 2021arXiv

1,529

citations

MViTv2: Improved Multiscale Vision Transformers for Classification and Detection

CVPR 2022arXiv

856

citations

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

CVPR 2022arXiv

247

citations

HiT: Hierarchical Transformer With Momentum Contrast for Video-Text Retrieval

ICCV 2021arXiv

167

citations

Unified Transformer Tracker for Object Tracking

CVPR 2022arXiv

106

citations

LLaVA-Critic: Learning to Evaluate Multimodal Models

CVPR 2025arXiv

103

citations

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

ICCV 2023arXiv

citations

Diffusion Models as Masked Autoencoders

ICCV 2023arXiv

citations

Reversible Vision Transformers

CVPR 2022arXiv

citations

On the Importance of Asymmetry for Siamese Representation Learning

CVPR 2022arXiv

citations

Multiview Pseudo-Labeling for Semi-Supervised Learning From Video

ICCV 2021arXiv

citations

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

CVPR 2023arXiv

citations

Beyond Short Clips: End-to-End Video-Level Learning With Collaborative Memories

CVPR 2021arXiv

citations

Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning

ICLR 2025arXiv

citations

Haoqi Fan

papers (18)

Momentum Contrast for Unsupervised Visual Representation Learning

Multiscale Vision Transformers

MViTv2: Improved Multiscale Vision Transformers for Classification and Detection

Masked Feature Prediction for Self-Supervised Visual Pre-Training

Scaling Language-Image Pre-Training via Masking

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

HiT: Hierarchical Transformer With Momentum Contrast for Video-Text Retrieval

Unified Transformer Tracker for Object Tracking

LLaVA-Critic: Learning to Evaluate Multimodal Models

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

Diffusion Models as Masked Autoencoders

Reversible Vision Transformers

On the Importance of Asymmetry for Siamese Representation Learning

Multiview Pseudo-Labeling for Semi-Supervised Learning From Video

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

Beyond Short Clips: End-to-End Video-Level Learning With Collaborative Memories

Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning

papers (18)

Momentum Contrast for Unsupervised Visual Representation Learning

Multiscale Vision Transformers

MViTv2: Improved Multiscale Vision Transformers for Classification and Detection

Masked Feature Prediction for Self-Supervised Visual Pre-Training

Scaling Language-Image Pre-Training via Masking

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

HiT: Hierarchical Transformer With Momentum Contrast for Video-Text Retrieval

Unified Transformer Tracker for Object Tracking

LLaVA-Critic: Learning to Evaluate Multimodal Models

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

Diffusion Models as Masked Autoencoders

Reversible Vision Transformers

On the Importance of Asymmetry for Siamese Representation Learning

Multiview Pseudo-Labeling for Semi-Supervised Learning From Video

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

Beyond Short Clips: End-to-End Video-Level Learning With Collaborative Memories

Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning