# Seg2Click

Training and inference implementation that predicts an executable-region mask and derives a GUI click from that mask.

- Catalog URL: https://awesomecua.github.io/resources/github-jcwang0602-seg2click/
- Original source: https://github.com/jcwang0602/Seg2Click
- Kind: framework
- Review: curated
- Scope: core
- Environments: cross-platform
- Topics: grounding, screen-understanding
- Evidence checked: 2026-10-17T01:46:05Z
- ID: github:jcwang0602/seg2click

## Limitations

The repository provides training, evaluation, and a custom mask decoder. Its code license does not determine the licenses of the five model checkpoints. No model execution was performed.

- Record JSON: https://awesomecua.github.io/resources/github-jcwang0602-seg2click/record.json

## License declarations

- code: MIT — https://raw.githubusercontent.com/jcwang0602/Seg2Click/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/jcwang0602/Seg2Click/HEAD/README.md (retrieved 2026-10-17T01:46:05Z; SHA-256 2316acbef1207925b10b4770e14bdf69f6f4b6b3bc0ddb12e6be107d6f1425da)
- https://raw.githubusercontent.com/jcwang0602/Seg2Click/HEAD/LICENSE (retrieved 2026-10-17T01:52:51Z; SHA-256 57bcc2eb985fa6036bf2bde7f28c4fd359c6b3479a658fea768162cac2a75ba5)
