6 papers
MoCrop: Training Free Motion Guided Cropping for Efficient Video Action Recognition
Binhua Huang, Wendong Yao, Shaowu Chen +3
Standard video action recognition models often process typically resized full frames, suffering from spatial redundancy and high computational costs. To address this, we introduce…
A multimodal Transformer for InSAR-based ground deformation forecasting with cross-site generalization across Europe
Wendong Yao, Binhua Huang, Soumyabrata Dev
Near-real-time regional-scale monitoring of ground deformation is increasingly required to support urban planning, critical infrastructure management, and natural hazard mitigation…
Multi-modal Spatio-Temporal Transformer for High-resolution Land Subsidence Prediction
Wendong Yao, Binhua Huang, Soumyabrata Dev
Forecasting high-resolution land subsidence is a critical yet challenging task due to its complex, non-linear dynamics. While standard architectures like ConvLSTM often fail to mod…
MoCLIP-Lite: Efficient Video Recognition by Fusing CLIP with Motion Vectors
Binhua Huang, Ni Wang, Arjun Pakrashi +1
Video action recognition is a fundamental task in computer vision, but state-of-the-art models are often computationally expensive and rely on extensive video pre-training. In para…
MVP: Motion Vector Propagation for Zero-Shot Video Object Detection
Binhua Huang, Ni Wang, Wendong Yao +1
Running a large open-vocabulary (Open-vocab) detector on every video frame is accurate but expensive. We introduce a training-free pipeline that invokes OWLv2 only on fixed-interva…
A Deep Learning Approach for Spatio-Temporal Forecasting of InSAR Ground Deformation in Eastern Ireland
Wendong Yao, Saeed Azadnejad, Binhua Huang +2
Monitoring ground displacement is crucial for urban infrastructure stability and mitigating geological hazards. However, forecasting future deformation from sparse Interferometric…