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

Add to Chrome

Add to Firefox

Picture for Jie Wu

Jie Wu

Masked Vision-Language Transformers for Scene Text Recognition

Nov 09, 2022
Jie Wu, Ying Peng, Shengming Zhang, Weigang Qi, Jian Zhang

Figure 1 for Masked Vision-Language Transformers for Scene Text Recognition

Figure 2 for Masked Vision-Language Transformers for Scene Text Recognition

Figure 3 for Masked Vision-Language Transformers for Scene Text Recognition

Figure 4 for Masked Vision-Language Transformers for Scene Text Recognition

* The paper is accepted by the 33rd British Machine Vision Conference (BMVC 2022)

Access Paper or Ask Questions

Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

Aug 22, 2022
Jie Qin, Jie Wu, Ming Li, Xuefeng Xiao, Min Zheng, Xingang Wang

Figure 1 for Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

Figure 2 for Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

Figure 3 for Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

Figure 4 for Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

* Accepted by ECCV2022

Access Paper or Ask Questions

Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Jun 22, 2022
Ming Li, Jie Wu, Jinhang Cai, Jie Qin, Yuxi Ren, Xuefeng Xiao, Min Zheng, Rui Wang, Xin Pan

Figure 1 for Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Figure 2 for Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Figure 3 for Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Figure 4 for Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

* The solution of 1st Place in AVA Accessibility Vision and Autonomy Challenge on CVPR 2022 workshop. Website: https://accessibility-cv.github.io/

Access Paper or Ask Questions

ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer

Mar 21, 2022
Rui Yang, Hailong Ma, Jie Wu, Yansong Tang, Xuefeng Xiao, Min Zheng, Xiu Li

Figure 1 for ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer

Figure 2 for ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer

Figure 3 for ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer

Figure 4 for ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer

* The code will be released

Access Paper or Ask Questions

Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions

Mar 20, 2022
Pingping Dai, Licong Dong, Ruihan Zhang, Haiming Zhu, Jie Wu, Kehong Yuan

Figure 1 for Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions

Figure 2 for Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions

Figure 3 for Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions

Figure 4 for Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions

* 9 pages, 6 figures, 1 table

Access Paper or Ask Questions

Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Jan 20, 2022
Yu Wang, Xinsheng Wang, Pengcheng Zhu, Jie Wu, Hanzhao Li, Heyang Xue, Yongmao Zhang, Lei Xie, Mengxiao Bi

Figure 1 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Figure 2 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Figure 3 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Figure 4 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

* will be submitted to Interspeech 2022

Access Paper or Ask Questions