Picture for Ying Zeng

Ying Zeng

ARS-DETR: Aspect Ratio Sensitive Oriented Object Detection with Transformer

Mar 09, 2023
Ying Zeng, Xue Yang, Qingyun Li, Yushi Chen, Junchi Yan

Figure 1 for ARS-DETR: Aspect Ratio Sensitive Oriented Object Detection with Transformer

Figure 2 for ARS-DETR: Aspect Ratio Sensitive Oriented Object Detection with Transformer

Figure 3 for ARS-DETR: Aspect Ratio Sensitive Oriented Object Detection with Transformer

Figure 4 for ARS-DETR: Aspect Ratio Sensitive Oriented Object Detection with Transformer

* 10 pages, 8 figures, 8 tables, the source code is available at https://github.com/httle/ARS-DETR

Access Paper or Ask Questions

Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations

Nov 12, 2022
Sijie Mai, Ying Zeng, Haifeng Hu

Figure 1 for Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations

Figure 2 for Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations

Figure 3 for Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations

Figure 4 for Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations

* This paper is accepted by IEEE Transactions on Multimedia. This version addresses some mistakes and typos in the original paper. The appendix is available at https://github.com/TmacMai/Multimodal-Information-Bottleneck/blob/main/appendix.pdf

Access Paper or Ask Questions

Taxonomy Completion via Triplet Matching Network

Jan 07, 2021
Jieyu Zhang, Xiangchen Song, Ying Zeng, Jiaze Chen, Jiaming Shen, Yuning Mao, Lei Li

Figure 1 for Taxonomy Completion via Triplet Matching Network

Figure 2 for Taxonomy Completion via Triplet Matching Network

Figure 3 for Taxonomy Completion via Triplet Matching Network

Figure 4 for Taxonomy Completion via Triplet Matching Network

* AAA1 2021

Access Paper or Ask Questions

Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion

Dec 02, 2020
Sijie Mai, Songlong Xing, Jiaxuan He, Ying Zeng, Haifeng Hu

Figure 1 for Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion

Figure 2 for Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion

Figure 3 for Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion

Figure 4 for Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion

* submitted to IEEE Trans on Cybernetics

Access Paper or Ask Questions

Xiaomingbot: A Multilingual Robot News Reporter

Jul 12, 2020
Runxin Xu, Jun Cao, Mingxuan Wang, Jiaze Chen, Hao Zhou, Ying Zeng, Yuping Wang, Li Chen, Xiang Yin, Xijin Zhang, Songcheng Jiang, Yuxuan Wang, Lei Li

Figure 1 for Xiaomingbot: A Multilingual Robot News Reporter

Figure 2 for Xiaomingbot: A Multilingual Robot News Reporter

Figure 3 for Xiaomingbot: A Multilingual Robot News Reporter

Figure 4 for Xiaomingbot: A Multilingual Robot News Reporter

* Accepted to ACL 2020 - system demonstration

Access Paper or Ask Questions

Importance-Aware Learning for Neural Headline Editing

Nov 25, 2019
Qingyang Wu, Lei Li, Hao Zhou, Ying Zeng, Zhou Yu

Figure 1 for Importance-Aware Learning for Neural Headline Editing

Figure 2 for Importance-Aware Learning for Neural Headline Editing

Figure 3 for Importance-Aware Learning for Neural Headline Editing

Figure 4 for Importance-Aware Learning for Neural Headline Editing

* AAAI 2020

Access Paper or Ask Questions