434 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Alibaba Group (China)CN14 papers
- Alibaba Group (Cayman Islands)KY6 papers
- Hong Kong Polytechnic UniversityHK5 papers
- Nanyang Technological UniversitySG4 papers
- Zhejiang UniversityCN4 papers
- Chinese Academy of SciencesCN2 papers
- Chinese University of Hong KongHK2 papers
- Harbin Institute of TechnologyCN2 papers
- Peng Cheng LaboratoryCN2 papers
- Renmin University of ChinaCN2 papers
- Tencent (China)CN2 papers
- Alibaba Group (United States)US1 paper
5 papers · 1 filter
Two Causal Principles for Improving Visual Dialog
Jiaxin Qi, Yulei Niu, Jianqiang Huang +1
This paper unravels the design tricks adopted by us, the champion team MReaL-BDAI, for Visual Dialog Challenge 2019: two causal principles for improving Visual Dialog (VisDial). By…
Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
Jiangnan Xia, Chen Wu, Ming Yan
This paper focuses on how to take advantage of external relational knowledge to improve machine reading comprehension (MRC) with multi-task learning. Most of the traditional method…
Hierarchical Pointer Net Parsing
Linlin Liu, Xiang Lin, Shafiq Joty +2
Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity. However, the decoder…
High Dimensional Similarity Search with Satellite System Graph: Efficiency, Scalability, and Unindexed Query Compatibility
Cong Fu, Changxu Wang, Deng Cai
Approximate Nearest Neighbor Search (ANNS) in high dimensional space is essential in database and information retrieval. Recently, there has been a surge of interest in exploring e…
Extreme Channel Prior Embedded Network for Dynamic Scene Deblurring
Jianrui Cai, Wangmeng Zuo, Lei Zhang
Recent years have witnessed the significant progress on convolutional neural networks (CNNs) in dynamic scene deblurring. While CNN models are generally learned by the reconstructi…