collaborators

20 papers

cs.CV2026

DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection for Privacy-Preserving Face Recognition

Zhihan Ren, Lijun He, Xinyao Wang +2

Split face recognition reduces client-side computation but exposes intermediate features to feature inversion attacks and unauthorized analysis by honest-but-curious (HBC) servers.…

cs.CV2026

SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates

Kaile Wang, Lijun He, Haisheng Fu +2

Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic inconsistency at ultra-low bitrates (bpp < 0.05), limiting its reliab…

cs.CV2026

Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection

Yixing Yong, Jian Wang, Ming Lei +2

Infrared object detection is crucial for perception in autonomous driving and surveillance but remains vulnerable to physical adversarial attacks. Unlike in the RGB domain, where a…

eess.SP2026

Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference

Jingyi Liu, Cheng Yuan, Lijun He +2

The expanding application of smart sensing has created a growing demand for the accurate understanding of human action at the network edge. Traditional approaches require massive v…

cs.CV2026

MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification

Zuzheng Kuang, Honghao Chang, Boqiang Liang +4

Open-vocabulary change detection aims to identify semantic changes in bi-temporal remote sensing images without predefined categories. Recent methods combine foundation models such…

cs.AI2026

Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration

Wei Dai, Haoyu Wang, Honghao Chang +4

Vision Language Model (VLM) typically assume complete modality input during inference. However, their effectiveness drops sharply when certain modalities are unavailable or incompl…