Yongming Li — accepted AI-conference papers

2025

BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution

Xue Yang, Tao Chen, Lei Guo, Wenbo Jiang, Ji Guo, Yongming Li +1

ICASSP 2025accepted

Reference-based image super-resolution (RefSR) represents a promising advancement in super-resolution (SR). In contrast to single-image super-resolution (SISR), RefSR leverages an additional reference image to help recover high-frequency details, yet its vulnerability to backdoor attacks has not bee…

Cited by 0 Source ↗Scholar ↗

2021

Bidirectional Focused Semantic Alignment Attention Network for Cross-Modal Retrieval

Shuli Cheng, Liejun Wang, Anyu Du, Yongming Li

ICASSP 2021accepted

Cross-modal retrieval is a very challenging and significant task in intelligent understanding. Researchers have tried to capture modal semantic information through a weighted attention mechanism. Still, they cannot eliminate irrelevant semantic information's negative effects and cannot capture fine-…

Cited by 0 Source ↗Scholar ↗