基本信息
views: 453
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
His primary research interests are Computer Vision, Machine Learning, and Multimedia. Specifically, he aims to build an efficient vision system that can understand complex visual scenes as humans. By “human-like”, we mean that the vision systems should be equipped with three types of abilities:
1) Explainable: The model should rely on (right) explicit evidences when making decisions, ie, right for the right reasons.
2) Robust: The model should be robust to some situations with only low-quality training data (eg, training samples are biased, noisy, or limited).
3) Universal: The model design is relatively universal, ie, it is expected to be effective for various tasks.
1) Explainable: The model should rely on (right) explicit evidences when making decisions, ie, right for the right reasons.
2) Robust: The model should be robust to some situations with only low-quality training data (eg, training samples are biased, noisy, or limited).
3) Universal: The model design is relatively universal, ie, it is expected to be effective for various tasks.
Research Interests
Papers共 103 篇Author StatisticsCo-AuthorSimilar Experts
By YearBy Citation主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCEno. 5 (2024): 3123-3136
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGYno. 1 (2024): 195-206
IEEE TRANSACTIONS ON IMAGE PROCESSINGno. 99 (2024): 2759-2769
IEEE transactions on pattern analysis and machine intelligenceno. 99 (2024): 1-20
CoRR (2024): 1084-1088
CoRR (2024)
Cited0Views0EIBibtex
0
0
CoRR (2024)
Cited0Views0EIBibtex
0
0
CoRR (2024)
Cited0Views0EIBibtex
0
0
Load More
Author Statistics
Co-Author
Co-Institution
D-Core
- 合作者
- 学生
- 导师
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn