Xudong Liu

9

Papers

48

Total Citations

Papers (9)

LEOD: Label-Efficient Object Detection for Event Cameras

Code-Style In-Context Learning for Knowledge-Based Question Answering

SpFormer: Spatio-Temporal Modeling for Scanpaths with Transformer

SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

High-Fidelity Clothed Avatar Reconstruction From a Single Image

DFM: Differentiable Feature Matching for Anomaly Detection

Cross-view Semantic Alignment for Livestreaming Product Recognition

IOP: An Idempotent-Like Optimization Method on the Pareto Front of Hypernetwork