Sample Correlation for Fingerprinting Deep Face Recognition

Information Science, Computer Science, Automation, Artificial Intelligence,
sample correlation   deep face recognition   model fingerprinting   model stealing attacks   JPEG compression   intellectual property protection   knowledge distillation  

Report on Academic Paper: “Sample Correlation for Fingerprinting Deep Face Recognition” Background and Research Problem In recent years, the rapid advancements in deep learning technologies have significantly propelled the development of face recognition. However, commercial face recognition models face increasing intellectual property (IP) threats...

A Displacement Uncertainty-Based Method for Multi-Object Tracking in Low-Frame-Rate Videos

Engineering, Electrical Engineering, Information Science, Computer Science, Automation, Artificial Intelligence,
multi-object tracking   low-frame-rate videos   occlusion handling   uncertainty   optical flow   online tracking   Bayesian deep learning  

The Academic Report on Low-Frame-Rate Multi-Object Tracking Introduction and Research Background In recent years, multi-object tracking (MOT) has been widely applied in intelligent video surveillance, autonomous driving, and robotics vision. However, traditional MOT methods are predominantly designed for high-frame-rate videos and face significant ...

Anti-Fake Vaccine: Safeguarding Privacy Against Face Swapping via Visual-Semantic Dual Degradation

Information Science, Computer Science, Artificial Intelligence,
privacy protection   face swapping   adversarial perturbation   deepfake   visual degradation   semantic degradation  

Deepfake and Facial Privacy Protection: Innovative Research on Anti-Fake Vaccine Background and Motivation In recent years, advancements in deepfake technology have posed severe threats to personal privacy and social security. Facial swapping, a typical application of deepfake technology, is widely used in filmmaking and computer games, but its ris...

Weakly Supervised Semantic Segmentation of Driving Scenes Based on Few Annotated Pixels and Point Clouds

Engineering, Transportation Engineering, Information Science, Computer Science,
weakly supervised   semantic segmentation   driving scenes   point cloud data   pseudo labels  

Few Annotated Pixels and Point Cloud Based Weakly Supervised Semantic Segmentation of Driving Scenes Background and Research Issues Semantic segmentation, a critical task in computer vision, has extensive applications in domains like autonomous driving. However, traditional fully-supervised semantic segmentation methods require exhaustive pixel-lev...

Rethinking Contemporary Deep Learning Techniques for Error Correction in Biometric Data

Engineering, Electrical Engineering, Information Science, Computer Science, Artificial Intelligence, Life Sciences, Bioengineering,
biometrics   secure sketch   error correction   maximum likelihood decoding   deep learning  

Rethinking Deep Learning Techniques for Error Correction in Biometric Data Background With the rapid development of information technology, biometric data has become increasingly important in identity verification and secure storage. Traditional cryptography relies on uniformly distributed and precisely reproducible random strings. However, most re...

Day2Dark: Pseudo-Supervised Activity Recognition Beyond Silent Daylight

Information Science, Electronic Information, Computer Science, Automation, Artificial Intelligence,
activity recognition   low-light conditions   audio-visual fusion   pseudo-supervised learning   darkness adaptation  

Research Highlights: Low-Light Activity Recognition Based on Pseudo-Supervision and Adaptive Audio-Visual Fusion Academic Context This paper investigates the challenges of recognizing activities under low-light conditions. While existing activity recognition technologies perform well in well-lit environments, they often fail when dealing with low-l...