Ensemble Learning for Fusion of Multiview Vision with Occlusion and Missing Information: Framework and Evaluations with Real-World Data and Applications in Driver Hand Activity Recognition
[article]
Ross Greer, Mohan Trivedi
2023
arXiv
pre-print
on within-group subjects, and that our multi-camera framework performs best on average in cross-group validation, and that the fusion approach outperforms ensemble weighted majority and model combination ...
Multi-sensor frameworks provide opportunities for ensemble learning and sensor fusion to make use of redundancy and supplemental information, helpful in real-world safety applications such as continuous ...
For the single view model, we make direct inference, and for the multi-view models, we pass the logits to ensemble algorithms, or pass the CNN-output feature maps to a neural network for late fusion. ...
arXiv:2301.12592v2
fatcat:siknw5hfxrh43hblhsnrhl5pra