DCA measures intra-sample representational consistency in frozen vision models by checking per-dimension coactivation across regions, achieving 0.91-0.93 AUC in deepfake detection with DINOv3 features.
ICCV , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.
citing papers explorer
-
Dimensional Coactivation for Representational Consistency in Frozen Vision Foundation Models
DCA measures intra-sample representational consistency in frozen vision models by checking per-dimension coactivation across regions, achieving 0.91-0.93 AUC in deepfake detection with DINOv3 features.
-
Learning to See What You Need: Gaze Attention for Multimodal Large Language Models
Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.