6 papers
DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version
Sean Bin Yang, Hao Miao, Zongyi Xu +5
Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in intelligent transportation s…
REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended Version
Sean Bin Yang, Ying Sun, Jilin Hu +5
Trajectory representation learning underpins a wide range of trajectory analytics tasks; however, most existing self-supervised approaches, whether discriminative or generative, ad…
PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer
Xiaoshui Huang, Tianlin Zhu, Yifan Zuo +7
Single-cell RNA sequencing (scRNA-seq) is essential for decoding tumor heterogeneity. However, pan-cancer research still faces two key challenges: learning discriminative and effic…
Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark
Zongyi Xu, Zhongpeng Lang, Yilong Chen +6
Cross-source point cloud registration, which aims to align point cloud data from different sensors, is a fundamental task in 3D vision. However, compared to the same-source point c…
Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation
Yilong Chen, Zongyi Xu, Xiaoshui Huang +4
Compared to single-modal knowledge distillation, cross-modal knowledge distillation faces more severe challenges due to domain gaps between modalities. Although various methods hav…
Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotation
Yilong Chen, Zongyi Xu, xiaoshui Huang +3
Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak superv…