← Search

Zengwen Li

2 accepted papers

2025

DSRC: Learning Density-Insensitive and Semantic-Aware Collaborative Representation Against Corruptions

AAAI 2025technical

As a potential application of Vehicle-to-Everything (V2X) communication, multi-agent collaborative perception has achieved significant success in 3D object detection. While these methods have demonstrated impressive results on standard benchmarks, the robustness of such approaches in the face of com…

2023

Learning 3D Human Pose and Shape Estimation Using Uncertainty-Aware Body Part Segmentation

ICASSP 2023accepted

While exploiting body segmentations for supervision, existing 3D human pose and shape estimation methods are plagued by mismatches between clothed body segmentations and skinned SMPL model reprojections. Moreover, noisy pixels introduced by inaccurate segmentation annotations also prevent the model…

Cited by 0SourceScholar