Search Results for author:
Found 6 papers, 3 papers with code
GaitPoint+: A Gait Recognition Network Incorporating Point Cloud Analysis and Recycling
Our approach models skeleton key points as a 3D point cloud, and employs a computational complexity-conscious 3D point processing approach to extract skeleton features, which are then combined with silhouette features for improved accuracy.
Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos
Our results show that this framework offers state-of-the-art performance on zero-shot transfer and video-based CLIP for predicting the driver's state on two public datasets.
ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling
Recent years have witnessed significant developments in point cloud processing, including classification and segmentation.
ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud Classification
Existing FSL methods for 3D point clouds employ point-based models as their backbone.
Ranked #1 on
Few-Shot Point Cloud Classification
on ModelNet40
Why Discard if You Can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis
In order to address this issue and improve the performance of any baseline 3D point classification or segmentation model, we propose a new module, referred to as the Recycling MaxPooling (RMP) module, to recycle and utilize the features of some of the discarded points.
Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation
As the core module of the DPFA-Net, we propose a Feature Aggregation layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism.
