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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Songyang Zhang

Songyang Zhang

SAT: 2D Semantics Assisted Training for 3D Visual Grounding


May 24, 2021
Zhengyuan Yang, Songyang Zhang, Liwei Wang, Jiebo Luo

Figure 1 for SAT: 2D Semantics Assisted Training for 3D Visual Grounding
Figure 2 for SAT: 2D Semantics Assisted Training for 3D Visual Grounding
Figure 3 for SAT: 2D Semantics Assisted Training for 3D Visual Grounding
Figure 4 for SAT: 2D Semantics Assisted Training for 3D Visual Grounding

  Access Paper or Ask Questions

Learning Implicit Temporal Alignment for Few-shot Video Classification


May 11, 2021
Songyang Zhang, Jiale Zhou, Xuming He

Figure 1 for Learning Implicit Temporal Alignment for Few-shot Video Classification
Figure 2 for Learning Implicit Temporal Alignment for Few-shot Video Classification
Figure 3 for Learning Implicit Temporal Alignment for Few-shot Video Classification
Figure 4 for Learning Implicit Temporal Alignment for Few-shot Video Classification
* Accepted by IJCAI 2021 
  Access Paper or Ask Questions

Video-aided Unsupervised Grammar Induction


May 04, 2021
Songyang Zhang, Linfeng Song, Lifeng Jin, Kun Xu, Dong Yu, Jiebo Luo

Figure 1 for Video-aided Unsupervised Grammar Induction
Figure 2 for Video-aided Unsupervised Grammar Induction
Figure 3 for Video-aided Unsupervised Grammar Induction
Figure 4 for Video-aided Unsupervised Grammar Induction
* This paper is accepted by NAACL'21 
  Access Paper or Ask Questions

Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation


Apr 29, 2021
Rongjie Li, Songyang Zhang, Bo Wan, Xuming He

* Accepted by CVPR2021 
  Access Paper or Ask Questions

Distribution Alignment: A Unified Framework for Long-tail Visual Recognition


Mar 30, 2021
Songyang Zhang, Zeming Li, Shipeng Yan, Xuming He, Jian Sun

Figure 1 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Figure 2 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Figure 3 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Figure 4 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

Boundary Proposal Network for Two-Stage Natural Language Video Localization


Mar 15, 2021
Shaoning Xiao, Long Chen, Songyang Zhang, Wei Ji, Jian Shao, Lu Ye, Jun Xiao

Figure 1 for Boundary Proposal Network for Two-Stage Natural Language Video Localization
Figure 2 for Boundary Proposal Network for Two-Stage Natural Language Video Localization
Figure 3 for Boundary Proposal Network for Two-Stage Natural Language Video Localization
Figure 4 for Boundary Proposal Network for Two-Stage Natural Language Video Localization
* AAAI 2021 
  Access Paper or Ask Questions

An Efficient Hypergraph Approach to Robust Point Cloud Resampling


Mar 11, 2021
Qinwen Deng, Songyang Zhang, Zhi Ding

Figure 1 for An Efficient Hypergraph Approach to Robust Point Cloud Resampling
Figure 2 for An Efficient Hypergraph Approach to Robust Point Cloud Resampling
Figure 3 for An Efficient Hypergraph Approach to Robust Point Cloud Resampling
Figure 4 for An Efficient Hypergraph Approach to Robust Point Cloud Resampling

  Access Paper or Ask Questions

Point Cloud Resampling Through Hypergraph Signal Processing


Feb 12, 2021
Qinwen Deng, Songyang Zhang, Zhi Ding

Figure 1 for Point Cloud Resampling Through Hypergraph Signal Processing
Figure 2 for Point Cloud Resampling Through Hypergraph Signal Processing
Figure 3 for Point Cloud Resampling Through Hypergraph Signal Processing
Figure 4 for Point Cloud Resampling Through Hypergraph Signal Processing

  Access Paper or Ask Questions

Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language


Dec 04, 2020
Songyang Zhang, Houwen Peng, Jianlong Fu, Yijuan Lu, Jiebo Luo

Figure 1 for Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language
Figure 2 for Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language
Figure 3 for Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language
Figure 4 for Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language

  Access Paper or Ask Questions

Content-based Analysis of the Cultural Differences between TikTok and Douyin


Nov 03, 2020
Li Sun, Haoqi Zhang, Songyang Zhang, Jiebo Luo

Figure 1 for Content-based Analysis of the Cultural Differences between TikTok and Douyin
Figure 2 for Content-based Analysis of the Cultural Differences between TikTok and Douyin
Figure 3 for Content-based Analysis of the Cultural Differences between TikTok and Douyin
Figure 4 for Content-based Analysis of the Cultural Differences between TikTok and Douyin
* Accepted by IEEE Big Data 2020 
  Access Paper or Ask Questions

Transformer with Bidirectional Decoder for Speech Recognition


Aug 11, 2020
Xi Chen, Songyang Zhang, Dandan Song, Peng Ouyang, Shouyi Yin

* Accepted by InterSpeech 2020 
  Access Paper or Ask Questions

Part-aware Prototype Network for Few-shot Semantic Segmentation


Jul 13, 2020
Yongfei Liu, Xiangyi Zhang, Songyang Zhang, Xuming He

Figure 1 for Part-aware Prototype Network for Few-shot Semantic Segmentation
Figure 2 for Part-aware Prototype Network for Few-shot Semantic Segmentation
Figure 3 for Part-aware Prototype Network for Few-shot Semantic Segmentation
Figure 4 for Part-aware Prototype Network for Few-shot Semantic Segmentation
* ECCV-2020 
  Access Paper or Ask Questions

From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation


Jul 01, 2020
Songyang Zhang, Han Zhang, Shuguang Cui, Zhi Ding

Figure 1 for From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation
Figure 2 for From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation
Figure 3 for From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation
Figure 4 for From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation

  Access Paper or Ask Questions

Global Image Sentiment Transfer


Jun 22, 2020
Jie An, Tianlang Chen, Songyang Zhang, Jiebo Luo

Figure 1 for Global Image Sentiment Transfer
Figure 2 for Global Image Sentiment Transfer
Figure 3 for Global Image Sentiment Transfer
Figure 4 for Global Image Sentiment Transfer

  Access Paper or Ask Questions

Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos


Jan 27, 2020
Songyang Zhang, Tolga Aktas, Jiebo Luo

Figure 1 for Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos
Figure 2 for Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos
Figure 3 for Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos
Figure 4 for Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos

  Access Paper or Ask Questions

Hypergraph Spectral Analysis and Processing in 3D Point Cloud


Jan 08, 2020
Songyang Zhang, Shuguang Cui, Zhi Ding

Figure 1 for Hypergraph Spectral Analysis and Processing in 3D Point Cloud
Figure 2 for Hypergraph Spectral Analysis and Processing in 3D Point Cloud
Figure 3 for Hypergraph Spectral Analysis and Processing in 3D Point Cloud
Figure 4 for Hypergraph Spectral Analysis and Processing in 3D Point Cloud

  Access Paper or Ask Questions

Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization


Dec 08, 2019
Songyang Zhang, Houwen Peng, Le Yang, Jianlong Fu, Jiebo Luo

Figure 1 for Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization
Figure 2 for Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization
Figure 3 for Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization
* This is our winner solution for the HACS Temporal Action Localization Challenge at ICCV 2019 
  Access Paper or Ask Questions

Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language


Dec 08, 2019
Songyang Zhang, Houwen Peng, Jianlong Fu, Jiebo Luo

Figure 1 for Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language
Figure 2 for Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language
Figure 3 for Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language
Figure 4 for Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language
* This paper is accepted by AAAI 2020 
  Access Paper or Ask Questions

Dynamic Context Correspondence Network for Semantic Alignment


Sep 08, 2019
Shuaiyi Huang, Qiuyue Wang, Songyang Zhang, Shipeng Yan, Xuming He

Figure 1 for Dynamic Context Correspondence Network for Semantic Alignment
Figure 2 for Dynamic Context Correspondence Network for Semantic Alignment
Figure 3 for Dynamic Context Correspondence Network for Semantic Alignment
Figure 4 for Dynamic Context Correspondence Network for Semantic Alignment
* ICCV 2019 
  Access Paper or Ask Questions

Exploiting Temporal Relationships in Video Moment Localization with Natural Language


Aug 11, 2019
Songyang Zhang, Jinsong Su, Jiebo Luo

Figure 1 for Exploiting Temporal Relationships in Video Moment Localization with Natural Language
Figure 2 for Exploiting Temporal Relationships in Video Moment Localization with Natural Language
Figure 3 for Exploiting Temporal Relationships in Video Moment Localization with Natural Language
Figure 4 for Exploiting Temporal Relationships in Video Moment Localization with Natural Language

  Access Paper or Ask Questions

LatentGNN: Learning Efficient Non-local Relations for Visual Recognition


May 28, 2019
Songyang Zhang, Shipeng Yan, Xuming He

Figure 1 for LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
Figure 2 for LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
Figure 3 for LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
Figure 4 for LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
* ICML 2019 
  Access Paper or Ask Questions

Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning


Jan 02, 2018
Yuhang Song, Main Xu, Songyang Zhang, Liangyu Huo

Figure 1 for Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning
Figure 2 for Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning
Figure 3 for Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning
Figure 4 for Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning

  Access Paper or Ask Questions