Code
- MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection [code]
- BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation [code]
- BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection [code]
- PredNet-based Unsupervised Pedestrian Pose Prediction [code]
- Leveraging Trajectory Prediction for Pedestrian Video Anomaly Detection [code]
Multiple Instance Learning for Data Integration
- Bi-Capacity Choquet Integral for Sensor Fusion with Label Uncertainty (Bi-MIChI) [code]
- Efficient Multi-Resolution Fusion for Remote Sensing Data with Label Uncertainty (MIMRF-BFM) [code]
- Multi-Resolution Multi-Modal Sensor Fusion For Remote Sensing Data With Label Uncertainty (MIMRF) [code]
- Multiple Instance Choquet Integral (MICI) for Classifier Fusion and Regression [code]
Hyperspectral Unmixing
- Beta Compositional Model (BCM) for Hyperspectral Unmixing [code]
Data
- PedX: pedestrians in intersection dataset [website][GitHub]
- MUUUFL Gulfport Hyperspectral and LiDAR dataset [GitHub][scene annotation]
For more, please see FCAV Lab datasets page and code page.