ComPrivDet detects privacy objects in compressed videos by reusing I-frame inferences and skipping over 80% of detections while maintaining over 96% accuracy.
Deep residual learning for image recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
HBR-Net-18 combines bias correction with residual networks to improve prostate cancer detection accuracy on hybrid multi-dimensional MRI data.
Proposes causal fingerprints via causality-decoupling in pre-trained diffusion residual latent space for improved source attribution across GANs and diffusion models.
citing papers explorer
-
ComPrivDet: Efficient Privacy Object Detection in Compressed Domains Through Inference Reuse
ComPrivDet detects privacy objects in compressed videos by reusing I-frame inferences and skipping over 80% of detections while maintaining over 96% accuracy.
-
Hybrid Multi-Dimensional MRI Prostate Cancer Detection via Hadamard Network-Based Bias Correction and Residual Networks
HBR-Net-18 combines bias correction with residual networks to improve prostate cancer detection accuracy on hybrid multi-dimensional MRI data.
-
Causal Fingerprints of AI Generative Models
Proposes causal fingerprints via causality-decoupling in pre-trained diffusion residual latent space for improved source attribution across GANs and diffusion models.