Intelligent recognition of counterfeit goods text based on BERT and multimodal feature fusion
Tinghao Wang, Yuheng Li, Weiping Li, Lijuan Zhou, Ning Luo · 2025
Read Intelligent recognition of counterfeit goods text based on BERT and multimodal feature fusion by Tinghao Wang, Yuheng Li, Weiping Li, Lijuan Zhou, Ning Luo (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12749867.txt.
Description
Tinghao Wang, Yuheng Li, Weiping Li, Lijuan Zhou, and Ning Luo build in a 2025 paper a tool to spot fake goods text. Fakes often copy a brand name with a sound alike or shape alike character swap. That text trick fools buyers and is hard to catch at scale online.
Their network pairs a corrector with a detector helper built on a language model. A light transformer block first flags suspect characters so they warp meaning less. Shape, sound, and sense traits of each character are fused to lift fix accuracy. A new data set of 289,851 samples was built to end the data drought in this niche. The tool topped past methods on that set and held up on three public sets.
Catalog record
| CREATOR | Tinghao Wang, Yuheng Li, Weiping Li, Lijuan Zhou, Ning Luo |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |