Shiyu Chang
- Computer Vision and Pattern Recognition top 0.5%
- Artificial Intelligence top 0.5%
- Media Technology top 1%
- Biomedical Engineering top 10%
- Signal Processing top 2%
- Co-authors
- Thomas S. HuangDing LiuMo YuZhangyang WangWei HanShuicheng YanGuo-Jun QiCharų C. Aggarwal
- Topics
- Topic Modeling (17 papers)Natural Language Processing Techniques (14 papers)Domain Adaptation and Few-Shot Learning (14 papers)
- Partner nations
- United StatesChinaSingapore
In The Last Decade
Shiyu Chang
102 papers receiving 3.7k citations
Hit Papers
Peers
Comparison fields: 5 of 146
- Computer Vision and Pattern Recognition 2.2k
- Artificial Intelligence 1.9k
- Media Technology 367
- Biomedical Engineering 360
- Signal Processing 300
Countries citing papers authored by Shiyu Chang
This map shows the geographic impact of Shiyu Chang's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Shiyu Chang with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Shiyu Chang more than expected).
Fields of papers citing papers by Shiyu Chang
This network shows the impact of papers produced by Shiyu Chang. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Shiyu Chang. The network helps show where Shiyu Chang may publish in the future.
Co-authorship network of co-authors of Shiyu Chang
This figure shows the co-authorship network connecting the top 25 collaborators of Shiyu Chang. A scholar is included among the top collaborators of Shiyu Chang based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Shiyu Chang. Shiyu Chang is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 3 | |
| 2 | 4 | |
| 3 | 2 | |
| 4 | 90 | |
| 5 | AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss | 39 |
| 6 | Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers | 9 |
| 7 | A Stratified Approach to Robustness for Randomly Smoothed Classifiers. | 1 |
| 8 | 68 | |
| 9 | Revisiting Pre-training: An Efficient Training Method for Image Classification | 2 |
| 10 | R 3 : Reinforced Ranker-Reader for Open-Domain Question Answering. | 88 |
| 11 | Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization | 27 |
| 12 | 45 | |
| 13 | 153 | |
| 14 | Dilated Recurrent Neural Networks | 66 |
| 15 | Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering | 49 |
| 16 | 3 | |
| 17 | 6 | |
| 18 | A joint optimization framework of sparse coding and discriminative clustering | 16 |
| 19 | A space alignment method for cold-start tv show recommendations | 4 |
| 20 | Localizing web videos from heterogeneous images | 1 |
About Shiyu Chang
Shiyu Chang is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Computational Mathematics, having authored 110 papers that have together received 3.8k indexed citations. Recurring topics across this work include Topic Modeling (17 papers), Natural Language Processing Techniques (14 papers) and Domain Adaptation and Few-Shot Learning (14 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (2.2k citations), Artificial Intelligence (1.9k citations) and Media Technology (367 citations). Shiyu Chang has collaborated with scholars based in United States, China and Singapore. Frequent co-authors include Thomas S. Huang, Ding Liu, Mo Yu, Zhangyang Wang, Wei Han, Shuicheng Yan, Guo-Jun Qi, Charų C. Aggarwal, Yifan Jiang and Jiliang Tang. Their work appears in journals such as IEEE Transactions on Image Processing, eLife and Frontiers in Oncology.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.