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

Add to Chrome

Add to Firefox

Picture for Songyang Zhang

Songyang Zhang

Dynamic Grained Encoder for Vision Transformers

Jan 10, 2023
Lin Song, Songyang Zhang, Songtao Liu, Zeming Li, Xuming He, Hongbin Sun, Jian Sun, Nanning Zheng

Figure 1 for Dynamic Grained Encoder for Vision Transformers

Figure 2 for Dynamic Grained Encoder for Vision Transformers

Figure 3 for Dynamic Grained Encoder for Vision Transformers

Figure 4 for Dynamic Grained Encoder for Vision Transformers

* Accepted by NeurIPS2021

Access Paper or Ask Questions

Exemplar-Based Radio Map Reconstruction of Missing Areas Using Propagation Priority

Sep 10, 2022
Songyang Zhang, Tianhang Yu, Jonathan Tivald, Brian Choi, Feng Ouyang, Zhi Ding

Figure 1 for Exemplar-Based Radio Map Reconstruction of Missing Areas Using Propagation Priority

Figure 2 for Exemplar-Based Radio Map Reconstruction of Missing Areas Using Propagation Priority

Figure 3 for Exemplar-Based Radio Map Reconstruction of Missing Areas Using Propagation Priority

Figure 4 for Exemplar-Based Radio Map Reconstruction of Missing Areas Using Propagation Priority

* To appear in 2022 IEEE Global Communications Conference (Globecom)

Access Paper or Ask Questions

Expanding Language-Image Pretrained Models for General Video Recognition

Aug 04, 2022
Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, Haibin Ling

Figure 1 for Expanding Language-Image Pretrained Models for General Video Recognition

Figure 2 for Expanding Language-Image Pretrained Models for General Video Recognition

Figure 3 for Expanding Language-Image Pretrained Models for General Video Recognition

Figure 4 for Expanding Language-Image Pretrained Models for General Video Recognition

* Accepted by ECCV2022, Oral

Access Paper or Ask Questions

Action Quality Assessment with Temporal Parsing Transformer

Jul 19, 2022
Yang Bai, Desen Zhou, Songyang Zhang, Jian Wang, Errui Ding, Yu Guan, Yang Long, Jingdong Wang

Figure 1 for Action Quality Assessment with Temporal Parsing Transformer

Figure 2 for Action Quality Assessment with Temporal Parsing Transformer

Figure 3 for Action Quality Assessment with Temporal Parsing Transformer

Figure 4 for Action Quality Assessment with Temporal Parsing Transformer

* accepted by ECCV 2022

Access Paper or Ask Questions

The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Jun 07, 2022
Lin Li, Long Chen, Yifeng Huang, Zhimeng Zhang, Songyang Zhang, Jun Xiao

Figure 1 for The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Figure 2 for The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Figure 3 for The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Figure 4 for The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

* Accepted by CVPR 2022

Access Paper or Ask Questions