← Search

Shengyao Chen

6 accepted papers

2026

VTONGuard: Automatic Detection and Authentication of AI-Generated Virtual Try-On Content

ICASSP 2026poster

With the rapid advancement of generative AI, virtual try-on (VTON) systems are becoming increasingly common in e-commerce and digital entertainment. However, the growing realism of AI-generated try-on content raises pressing concerns about authenticity and responsible use. To address this, we presen…

Cited by 0SourcePDFScholar
2024

TransMUSIC: A Transformer-Aided Subspace Method for DOA Estimation with Low-Resolution ADCS

ICASSP 2024accepted

Direction of arrival (DOA) estimation employing low-resolution analog-to-digital convertors (ADCs) has emerged as a challenging and intriguing problem, particularly with the rise in popularity of large-scale arrays. The substantial quantization distortion complicates the extraction of signal and noi…

Cited by 0SourceScholar
2021

A Low-Complexity MIMO Dual Function Radar Communication System via One-Bit Sampling

ICASSP 2021accepted

Dual-function radar-communication (DFRC) system is flexible to be applied in a variety of scenarios. However, it is challenging to implement a low-cost low-complexity DFRC system due to the dynamic cooperation between radar sensing and communication tasks. In this paper, we propose to implement a lo…

Cited by 0SourceScholar
2017

Super-resolution delay-Doppler estimation for sub-Nyquist radar via atomic norm minimization

ICASSP 2017accepted

This paper studies the estimation of the delay and Doppler parameters of the sub-Nyquist radars. By formulating the delay-Doppler estimation as the low-rank matrix recovery, we propose an atomic norm minimization-based estimation approach. With the recovered low-rank matrix, we determine and pair th…

Cited by 0SourceScholar
2016

A segment-sliding reconstruction scheme for pulsed radar echoes with sub-Nyquist sampling

ICASSP 2016accepted

For radar echoes sampled at sub-Nyquist rates, it is impractical, if not impossible, to recover full-range Nyquist samples because of huge storage and computational loads. By exploiting the banded structure of the measurement matrix, we develop a novel segment-sliding reconstruction (SegSR) scheme t…

Cited by 0SourceScholar