Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport to enforce consistent attribute trajectories while preserving reference identity.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
EmoS is a new high-fidelity benchmark for fine-grained streaming emotional understanding that produces measurable gains when used to fine-tune multimodal large language models.
Pre-trained VGG19 features with bagged decision tree selection and SVM classification achieve 0.994 AUC for mass vs non-mass detection on the INbreast mammogram dataset.
citing papers explorer
-
Controlla: Learning Controllability via Graph-Constrained Latent Geometry
Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport to enforce consistent attribute trajectories while preserving reference identity.
-
EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding
EmoS is a new high-fidelity benchmark for fine-grained streaming emotional understanding that produces measurable gains when used to fine-tune multimodal large language models.
-
Automatic Mass Detection in Breast Using Deep Convolutional Neural Network and SVM Classifier
Pre-trained VGG19 features with bagged decision tree selection and SVM classification achieve 0.994 AUC for mass vs non-mass detection on the INbreast mammogram dataset.