Haoyu Ma

Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization

Zhengang Li, Mengshu Sun, Alec Lu et al. · 2022 · 62 citations

Model Quantization, Image Analysis, Machine Vision +14

EI-CLIP: Entity-aware Interventional Contrastive Learning for E-commerce Cross-modal Retrieval

Haoyu Ma, Handong Zhao, Zhe Lin et al. · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 55 citations

Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation

Yifei Chen, Haoyu Ma, Deying Kong et al. · 2020 · 43 citations

Geometric Learning, Convolutional Neural Network, Hand Pose Estimation +18

TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation

Haoyu Ma, Liangjian Chen, Deying Kong et al. · arXiv (Cornell University) · 2021 · 36 citations · Full text

Engineering, Human Pose Estimation, 3D Pose Estimation +17

VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer

Mengshu Sun, Haoyu Ma, Guoliang Kang et al. · arXiv (Cornell University) · 2022 · 28 citations · Full text

Engineering, Hardware Algorithm, Computer Architecture +17