Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Hao Liu

Hao Liu

RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating

Jul 19, 2022
Xulong Shi, Zhi Qi, Jiaxuan Cai, Keqi Fu, Yaru Zhao, Zan Li, Xuanyu Liu, Hao Liu

Figure 1 for RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating

Figure 2 for RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating

Figure 3 for RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating

Figure 4 for RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating

* This paper has absolutely nothing to do with repvgg, rep means repeating

Access Paper or Ask Questions

Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting

Jul 12, 2022
Hao Liu, Bin Chen, Bo Wang, Chunpeng Wu, Feng Dai, Peng Wu

Figure 1 for Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting

Figure 2 for Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting

Figure 3 for Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting

Figure 4 for Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting

* ACM Multimedia 2022

Access Paper or Ask Questions

GMN: Generative Multi-modal Network for Practical Document Information Extraction

Jul 11, 2022
Haoyu Cao, Jiefeng Ma, Antai Guo, Yiqing Hu, Hao Liu, Deqiang Jiang, Yinsong Liu, Bo Ren

Figure 1 for GMN: Generative Multi-modal Network for Practical Document Information Extraction

Figure 2 for GMN: Generative Multi-modal Network for Practical Document Information Extraction

Figure 3 for GMN: Generative Multi-modal Network for Practical Document Information Extraction

Figure 4 for GMN: Generative Multi-modal Network for Practical Document Information Extraction

* Accepted to NAACL 2022 main conference

Access Paper or Ask Questions

Masked World Models for Visual Control

Jun 28, 2022
Younggyo Seo, Danijar Hafner, Hao Liu, Fangchen Liu, Stephen James, Kimin Lee, Pieter Abbeel

Figure 1 for Masked World Models for Visual Control

Figure 2 for Masked World Models for Visual Control

Figure 3 for Masked World Models for Visual Control

Figure 4 for Masked World Models for Visual Control

* Project website: https://sites.google.com/view/mwm-rl

Access Paper or Ask Questions

Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes

Jun 25, 2022
Sugirtha T, Sridevi M, Khailash Santhakumar, Hao Liu, B Ravi Kiran, Thomas Gauthier, Senthil Yogamani

Figure 1 for Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes

Figure 2 for Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes

Figure 3 for Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes

Figure 4 for Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes

* Published at ICCVW-SSLAD 2021. arXiv admin note: substantial text overlap with arXiv:2104.10786

Access Paper or Ask Questions