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

Add to Chrome

Add to Firefox

Picture for Zehuan Yuan

Zehuan Yuan

Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

Jan 10, 2023
Keyu Tian, Yi Jiang, Qishuai Diao, Chen Lin, Liwei Wang, Zehuan Yuan

Figure 1 for Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

Figure 2 for Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

Figure 3 for Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

Figure 4 for Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

* v2: fixed some formatting errors

Access Paper or Ask Questions

QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query

Dec 15, 2022
Yabo Xiao, Kai Su, Xiaojuan Wang, Dongdong Yu, Lei Jin, Mingshu He, Zehuan Yuan

Figure 1 for QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query

Figure 2 for QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query

Figure 3 for QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query

Figure 4 for QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query

* Published on NeurIPS 2022

Access Paper or Ask Questions

Learning Object-Language Alignments for Open-Vocabulary Object Detection

Nov 27, 2022
Chuang Lin, Peize Sun, Yi Jiang, Ping Luo, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan, Jianfei Cai

Figure 1 for Learning Object-Language Alignments for Open-Vocabulary Object Detection

Figure 2 for Learning Object-Language Alignments for Open-Vocabulary Object Detection

Figure 3 for Learning Object-Language Alignments for Open-Vocabulary Object Detection

Figure 4 for Learning Object-Language Alignments for Open-Vocabulary Object Detection

* Technical Report

Access Paper or Ask Questions

Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

Oct 09, 2022
Haosen Yang, Deng Huang, Bin Wen, Jiannan Wu, Hongxun Yao, Yi Jiang, Xiatian Zhu, Zehuan Yuan

Figure 1 for Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

Figure 2 for Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

Figure 3 for Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

Figure 4 for Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

* 17 pages, 6 figures

Access Paper or Ask Questions

Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

Sep 27, 2022
Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

Figure 1 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

Figure 2 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

Figure 3 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

Figure 4 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

* 18 pages, 7 figures, Accepted by Neurips 2022

Access Paper or Ask Questions

Rethinking Resolution in the Context of Efficient Video Recognition

Sep 26, 2022
Chuofan Ma, Qiushan Guo, Yi Jiang, Zehuan Yuan, Ping Luo, Xiaojuan Qi

Figure 1 for Rethinking Resolution in the Context of Efficient Video Recognition

Figure 2 for Rethinking Resolution in the Context of Efficient Video Recognition

Figure 3 for Rethinking Resolution in the Context of Efficient Video Recognition

Figure 4 for Rethinking Resolution in the Context of Efficient Video Recognition

* Accepted by NIPS2022

Access Paper or Ask Questions

MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation

Sep 09, 2022
Zhenchao Jin, Dongdong Yu, Zehuan Yuan, Lequan Yu

Figure 1 for MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation

Figure 2 for MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation

Figure 3 for MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation

Figure 4 for MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation

* Accepted by TPAMI, codes are available at https://github.com/SegmentationBLWX/sssegmentation

Access Paper or Ask Questions