VT-SCC: Visual-text semantic alignment via multimodal guidance for unified staple crop organ counting
Lanying Wang, Zhengbo Liu, Xinyu Dong, Hainan Wang, Wei Guo, Yuanyuan Xiao, Qi Wang · 2026
Read VT-SCC: Visual-text semantic alignment via multimodal guidance for unified staple crop organ counting by Lanying Wang, Zhengbo Liu, Xinyu Dong, Hainan Wang, Wei Guo, Yuanyuan Xiao, Qi Wang (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/PMC13561956.txt.
Description
Wang and colleagues present in 2026 VT-SCC, a computer vision system that counts crop organs such as wheat ears and maize kernels by combining images with written category descriptions. Counting yield organs drives breeding decisions, but dense field scenes fool purely visual counters.
Two parts do the work. A scale-adaptive aggregator gathers features at several sizes so organs of very different dimensions register properly. Meanwhile a semantic channel modulator uses text prompts naming the target to tune the visual features and suppress background clutter. Across a dataset covering wheat, maize, rice, and soybean, the system's average counting error came in lower than existing generic few-shot counters. It also stayed close to models built for one crop only, within a few organs per image on the reported error measures. It also adapted to unseen domains with only a handful of examples.
Catalog record
| CREATOR | Lanying Wang, Zhengbo Liu, Xinyu Dong, Hainan Wang, Wei Guo, Yuanyuan Xiao, Qi Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |