Shuangrui Ding
University of Michigan
16 Papers
22 Citations
Shuangrui Ding is an academic researcher from University of Michigan. The author has contributed to research in topics: Computer science & Motion (physics). The author has an hindex of 3, co-authored 3 publications.
Chat about Author
Papers
InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition
Pan Zhang,Xiaoyi Wang,Yuhang Cao,Chao Xu,Linke Ouyang,Zhiyuan Zhao,Shuangrui Ding,Songyang Zhang,Haodong Duan,H. Yan,Xin Zhang,Wei Li,Jingwen Li,Kai Chen,Conghui He,Xingcheng Zhang,Yu Qiao,Da Lin,Jiaqi Wang +18 more
TL;DR: This work proposes InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition that achieves competitive text-image composition scores compared to public solutions, including GPT4-V and GPT3.5.
•Posted Content
Towards More Practical Adversarial Attacks on Graph Neural Networks
TL;DR: This work shows that the common gradient-based white-box attacks can be generalized to the black-box setting via the connection between the gradient and an importance score similar to PageRank, and proposes a greedy procedure to correct the importance score that takes into account of the diminishing-return pattern.
65
•Proceedings Article
Towards More Practical Adversarial Attacks on Graph Neural Networks
Jiaqi Ma,Shuangrui Ding,Qiaozhu Mei +2 more
- 01 Jan 2020
TL;DR: In this article, the authors proposed a greedy procedure to correct the importance score that takes into account of the diminishing-return pattern, which can significantly increase the misclassification rate of common GNNs.
Dual Contrastive Learning for Spatio-temporal Representation
Shuangrui Ding,Rui Qian,Hongkai Xiong +2 more
- 12 Jul 2022
TL;DR: A novel dual contrastive formulation is presented that learns effective spatio-temporal representations and obtains state-of-the-art or comparable performance on UCF-101, HMDB-51, and Diving-48 datasets.
Motion-inductive Self-supervised Object Discovery in Videos
TL;DR: A model for directly processing consecutive RGB frames, and infer the optical flow between any pair of frames using a layered representation, with the opacity channels being treated as the segmentation, is proposed.