Jikang Cheng

Orcid: 0000-0001-6549-6148

According to our database1, Jikang Cheng authored at least 17 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
CoRR, May, 2026

Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection.
CoRR, March, 2026

IDRetracor: Towards Visual Forensics against Malicious Face Swapping.
ACM Trans. Multim. Comput. Commun. Appl., February, 2026

2025
A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World.
CoRR, December, 2025

When Generative Replay Meets Evolving Deepfakes: Domain-Aware Relative Weighting for Incremental Face Forgery Detection.
CoRR, November, 2025

ED<sup>4</sup>: Explicit Data-Level Debiasing for Deepfake Detection.
IEEE Trans. Image Process., 2025

Adversarial intensity awareness for robust object detection.
Comput. Vis. Image Underst., 2025

Generalization-Preserved Learning: Closing the Backdoor to Catastrophic Forgetting in Continual Deepfake Detection.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Entropy-Adaptive Diffusion Policy Optimization with Dynamic Step Alignment.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension.
CoRR, 2024

IDRetracor: Towards Visual Forensics Against Malicious Face Swapping.
CoRR, 2024

DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World.
CoRR, 2024

Can We Leave Deepfake Data Behind in Training Deepfake Detector?
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
Stylized image denoising via noise style transfer and Quasi Siamese network.
Signal Process. Image Commun., July, 2023

Promoting adversarial transferability with enhanced loss flatness.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2023

2021
"One-Shot" Super-Resolution via Backward Style Transfer for Fast High-Resolution Style Transfer.
IEEE Signal Process. Lett., 2021


  Loading...