{"id":"oscr:b:J92JEXR63EGSD-X","url":"https://openscicode.org/b/oscr:b:J92JEXR63EGSD-X","status":"current","doi":"10.3389/frai.2026.1771088","since":"2026-11-14","page":"doi_10.3389_frai.2026.1771088","repo":"github.com/mengyuligit/mae-funet-mri-finetune","commit":"e2c0f21a5c9f18304b04438edcacc3c41f4e809f","path":"modeling/conformer/transconv.py","swhid":"swh:1:cnt:4b407cb8c9763d8a06937c506f73d39b93fe6edb","lines":[1261,1403],"symbol":"TransConvRawSeg.forward","paragraphs":[[43,"Materials and methods › Segmentation with fused embedding › MAE fusion architect"]],"method":"lexical-v1","origin":"machine","paper":"https://doi.org/10.3389/frai.2026.1771088","swhid_qualified":"swh:1:cnt:4b407cb8c9763d8a06937c506f73d39b93fe6edb;origin=https://github.com/mengyuligit/mae-funet-mri-finetune;anchor=swh:1:rev:e2c0f21a5c9f18304b04438edcacc3c41f4e809f;path=/modeling/conformer/transconv.py;lines=1261-1403","reader":"https://openscicode.org/paper/doi_10.3389_frai.2026.1771088/?path=modeling%2Fconformer%2Ftransconv.py#L1261-L1403","citation":"Code block oscr:b:J92JEXR63EGSD-X (https://openscicode.org/b/oscr:b:J92JEXR63EGSD-X)\nmodeling/conformer/transconv.py, lines 1261 to 1403, in github.com/mengyuligit/mae-funet-mri-finetune (https://github.com/mengyuligit/mae-funet-mri-finetune), commit e2c0f21a5c9f18304b04438edcacc3c41f4e809f.\nPaper: https://doi.org/10.3389/frai.2026.1771088\nSWHID: swh:1:cnt:4b407cb8c9763d8a06937c506f73d39b93fe6edb;origin=https://github.com/mengyuligit/mae-funet-mri-finetune;anchor=swh:1:rev:e2c0f21a5c9f18304b04438edcacc3c41f4e809f;path=/modeling/conformer/transconv.py;lines=1261-1403"}