CIRThan is a new sketch+text composed image retrieval dataset for Thangka imagery with 2,287 images, sketches, and multi-level hierarchical texts.
InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
WRF4CIR uses weight-regularized fine-tuning with adversarial perturbations to mitigate overfitting in composed image retrieval and narrows the generalization gap on benchmarks.
citing papers explorer
-
A Sketch+Text Composed Image Retrieval Dataset for Thangka
CIRThan is a new sketch+text composed image retrieval dataset for Thangka imagery with 2,287 images, sketches, and multi-level hierarchical texts.
-
WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval
WRF4CIR uses weight-regularized fine-tuning with adversarial perturbations to mitigate overfitting in composed image retrieval and narrows the generalization gap on benchmarks.