ATM-Net fuses anatomy-aware text prompts with image features through ATPG, HASF, and CCAE modules to outperform prior methods on fine-grained lumbar spine segmentation in MRSpineSeg and SPIDER datasets.
Test- time prompt tuning for zero-shot generalization in vision- language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Anatomy-Aware Text-Visual Fusion with Dual-Perspective Prompts for Fine-Grained Lumbar Spine Segmentation
ATM-Net fuses anatomy-aware text prompts with image features through ATPG, HASF, and CCAE modules to outperform prior methods on fine-grained lumbar spine segmentation in MRSpineSeg and SPIDER datasets.