5 papers · 1 filter
Learning to Segment Liquids in Real-world Images
Jonas Li, Michelle Li, Luke Liu +2
Liquids like water, wine and medicine are everywhere. However, limited attention has been given to the task of segmenting liquids, hindering the ability of robots to safely avoid a…
PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
Yifan Jiao, Xinran Liu, Xiaoqiong Liu +3
Planar tracking has drawn increasing interest owing to its key roles in robotics and augmented reality. Despite recent great advancement, further development of planar tracking, pa…
IRDFusion: Iterative Relation-Map Difference guided Feature Fusion for Multispectral Object Detection
Jifeng Shen, Haibo Zhan, Xin Zuo +4
Current multispectral object detection methods often retain extraneous background or noise during feature fusion, limiting perceptual performance. To address this, we propose an in…
G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
Haiqing Ren, Zhongkai Luo, Heng Fan +3
Graph Convolutional Networks (GCNs) have proven to be highly effective for skeleton-based action recognition, primarily due to their ability to leverage graph topology for feature…
Benchmarking the Robustness of UAV Tracking Against Common Corruptions
Xiaoqiong Liu, Yunhe Feng, Shu Hu +2
The robustness of unmanned aerial vehicle (UAV) tracking is crucial in many tasks like surveillance and robotics. Despite its importance, little attention is paid to the performanc…