activity
20142024
most citedFacial Feature Point Detection: A Comprehensive Survey

48 citations · 62 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2024

Improving Adversarial Robustness via Decoupled Visual Representation Masking

Decheng Liu, Tao Chen, Chunlei Peng +3

Deep neural networks are proven to be vulnerable to fine-designed adversarial examples, and adversarial defense algorithms draw more and more attention nowadays. Pre-processing bas…

cs.CV2024

Imperceptible Face Forgery Attack via Adversarial Semantic Mask

Decheng Liu, Qixuan Su, Chunlei Peng +2

With the great development of generative model techniques, face forgery detection draws more and more attention in the related field. Researchers find that existing face forgery mo…

cs.CV20231 cited

Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model

Decheng Liu, Xijun Wang, Chunlei Peng +3

Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition…

cs.CV2023

Gradient constrained sharpness-aware prompt learning for vision-language models

Liangchen Liu, Nannan Wang, Dawei Zhou +4

This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i.e., improving the performance on unseen classes while maintaining…

cs.CV2023

Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection

Decheng Liu, Tao Chen, Chunlei Peng +3

Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security. Existing forg…

cs.CV20232 cited

PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow

Lin Yuan, Kai Liang, Xiao Pu +5

This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single…