8 papers
Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning
Monan Sun, Bangzhen Liu, Huaidong Zhang +1
Autoregressive models have emerged as an effective paradigm for point cloud generation. However, most existing approaches rely on heuristic tokenization strategies, such as spatial…
ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition
Ronggang Huang, Haoxin Yang, Yan Cai +3
3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in…
SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation
Weihong Chen, Xuemiao Xu, Haoxin Yang +5
Existing 3D Human Pose Estimation (HPE) methods achieve high accuracy but suffer from computational overhead and slow inference, while knowledge distillation methods fail to addres…
SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation
Jingdan Kang, Haoxin Yang, Yan Cai +4
Image generation technology has brought significant advancements across various fields but has also raised concerns about data misuse and potential rights infringements, particular…
Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning
Bangzhen Liu, Chenxi Zheng, Xuemiao Xu +3
The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness a…
VrdONE: One-stage Video Visual Relation Detection
Xinjie Jiang, Chenxi Zheng, Xuemiao Xu +4
Video Visual Relation Detection (VidVRD) focuses on understanding how entities interact over time and space in videos, a key step for gaining deeper insights into video scenes beyo…