3 papers
cs.CV2026
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…
cs.CV2025
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…
cs.CV2025
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…