5 papers · 1 filter
Parameter-Efficient Fine-Tuning for Spiking Point Cloud Models
Zihao Guo, Jihua Zhu, Yiding Sun +2
Spiking Neural Networks (SNNs) offer energy-efficient solutions for point cloud analysis on resource-constrained devices through event-driven computation. However, existing pre-tra…
GaussFusion: Towards Multimodal 3D Gaussian Pretraining
Zhixuan You, Jihua Zhu, Yiding Sun +5
3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre…
Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models
Zihao Guo, Jihua Zhu, Jian Liu +1
Pre-trained 3D point cloud foundation models (PFMs) have demonstrated strong transferability across diverse downstream tasks. However, full fine-tuning these models is computationa…
RA-Det: Towards Universal Detection of AI-Generated Images via Robustness Asymmetry
Xinchang Wang, Yunhao Chen, Yuechen Zhang +4
Recent image generators produce photo-realistic content that undermines the reliability of downstream recognition systems. As visual appearance cues become less pronounced, appeara…
Focus on What Matters: Constraining Spatial-Temporal Attention via Action-Units for Noise-Resilient AQA
Shuaikang Zhu, Yiding Sun, Zihao Guo +2
The core challenge in Action Quality Assessment (AQA) lies in extracting fine-grained motion features from redundant and complex video backgrounds. Existing global feature learning…