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

Add to Chrome

Add to Firefox

Picture for Wenxiao Wang

Wenxiao Wang

CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

Mar 13, 2023
Wenxiao Wang, Wei Chen, Qibo Qiu, Long Chen, Boxi Wu, Binbin Lin, Xiaofei He, Wei Liu

Figure 1 for CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

Figure 2 for CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

Figure 3 for CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

Figure 4 for CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

* 15 pages, 7 figures

Access Paper or Ask Questions

General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

Feb 20, 2023
Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai, Xiaofei He

Figure 1 for General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

Figure 2 for General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

Figure 3 for General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

Figure 4 for General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

* 14 pages, 4 figures

Access Paper or Ask Questions

Temporal Robustness against Data Poisoning

Feb 07, 2023
Wenxiao Wang, Soheil Feizi

Figure 1 for Temporal Robustness against Data Poisoning

Figure 2 for Temporal Robustness against Data Poisoning

Figure 3 for Temporal Robustness against Data Poisoning

Figure 4 for Temporal Robustness against Data Poisoning

* 11 pages, 7 figures

Access Paper or Ask Questions

CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Dec 20, 2022
Yuqi Lin, Minghao Chen, Wenxiao Wang, Boxi Wu, Ke Li, Binbin Lin, Haifeng Liu, Xiaofei He

Figure 1 for CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Figure 2 for CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Figure 3 for CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Figure 4 for CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

* 13 pages, 8 figures

Access Paper or Ask Questions

OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

Dec 20, 2022
Chenxi Huang, Tong He, Haidong Ren, Wenxiao Wang, Binbin Lin, Deng Cai

Figure 1 for OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

Figure 2 for OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

Figure 3 for OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

Figure 4 for OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

* 9 pages, 9 figures

Access Paper or Ask Questions

One-shot Implicit Animatable Avatars with Model-based Priors

Dec 05, 2022
Yangyi Huang, Hongwei Yi, Weiyang Liu, Haofan Wang, Boxi Wu, Wenxiao Wang, Binbin Lin, Debing Zhang, Deng Cai

Figure 1 for One-shot Implicit Animatable Avatars with Model-based Priors

Figure 2 for One-shot Implicit Animatable Avatars with Model-based Priors

Figure 3 for One-shot Implicit Animatable Avatars with Model-based Priors

Figure 4 for One-shot Implicit Animatable Avatars with Model-based Priors

* Project website: https://elicit3d.github.io

Access Paper or Ask Questions