Jingdong Wang

Group $K$-Means

2015 · arXiv (Cornell University)

We study how to learn multiple dictionaries from a dataset, and approximate any data point by the sum of the codewords each chosen from the corresponding dictionary. Although theoretically low approximation errors can be achieved …

Development Trend of Code Defect Detection Technology Based on Natural Language Processing

2024

Traditional defect detection research is based on program analysis, and when dealing with large-scale programs, the detection speed is usually slow, resulting in limited detection performance. Moreover, because traditional defect detection can only extract basic …