A fine-tuned multimodal score model with soft Q-Align scoring, element-conditioned prompts, and self-training on validation pseudo-labels takes first place in NTIRE 2025 Track 1 image-text alignment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Instruction-augmented Multimodal Alignment for Image-Text and Element Matching
A fine-tuned multimodal score model with soft Q-Align scoring, element-conditioned prompts, and self-training on validation pseudo-labels takes first place in NTIRE 2025 Track 1 image-text alignment.