17 citations · 26 across the 6 of their papers we have counts for
7 papers
Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation
Kanglin Qu, Pan Gao, Qun Dai +1
Synergistically capturing intricate local structures and global contextual dependencies has become a critical challenge in point cloud representation learning. To address this, we…
CloudMamba: Grouped Selective State Spaces for Point Cloud Analysis
Kanglin Qu, Pan Gao, Qun Dai +3
Due to the long-range modeling ability and linear complexity property, Mamba has attracted considerable attention in point cloud analysis. Despite some interesting progress, relate…
InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
Liangjian Wen, Qun Dai, Jianzhuang Liu +7
In multimodal representation learning, synergistic interactions between modalities not only provide complementary information but also create unique outcomes through specific inter…
HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning
Kanglin Qu, Pan Gao, Qun Dai +1
The attention mechanism has become a dominant operator in point cloud learning, but its quadratic complexity leads to limited inter-point interactions, hindering long-range depende…
Uncertainty Guided Refinement for Fine-Grained Salient Object Detection
Yao Yuan, Pan Gao, Qun Dai +2
Recently, salient object detection (SOD) methods have achieved impressive performance. However, salient regions predicted by existing methods usually contain unsaturated regions an…
MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature
Qun Dai, Chunyang Yuan, Yimian Dai +6
Land Surface Temperature (LST) is a critical parameter for environmental studies, but directly obtaining high spatial resolution LST data remains challenging due to the spatio-temp…
Unified Unsupervised Salient Object Detection via Knowledge Transfer
Yao Yuan, Wutao Liu, Pan Gao +2
Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks su…