IRA-YOLO: Inter-Class Relation Attention for PPE Detection in Industrial Scenes
Ran Zhao, Haoran Duan, Xiaodong Liu, Nan Xu, Junlin Du, Pei Zhou · 2026
Read IRA-YOLO: Inter-Class Relation Attention for PPE Detection in Industrial Scenes by Ran Zhao, Haoran Duan, Xiaodong Liu, Nan Xu, Junlin Du, Pei Zhou (2026) 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-13611384.txt.
Description
Ran Zhao and his team add class-tie heed to a much-used thing-find tool to spot gear that guards the wearer in plant scenes. Their 2026 study takes up blocked views, size shifts, and mess that make safe gear hard to spot.
Guard groups track ties in the world of things. A helm goes with a head, and gloves go with hands. The new part throws pic traits into class-based spaces. It learns which-way ties twixt group maps. That tie news feeds back into the traits used to find things. On a yard-stick set of pics, right calls rose past the base tool. The new part added few weights and kept finds fast. Tests on more than one set backed that the fine step moves well to more plant safe gear sets.
Catalog record
| CREATOR | Ran Zhao, Haoran Duan, Xiaodong Liu, Nan Xu, Junlin Du, Pei Zhou |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |