activity
20162026
most citedApplying Deep Bidirectional LSTM and Mixture Density Network for Basketball Trajectory Prediction

79 citations · 185 across the 14 of their papers we have counts for

collaborators
Showing 2019Show all

1 paper · 1 filter

cs.CV2019

Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision

Panagiotis Meletis, Rob Romijnders, Gijs Dubbelman

Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data. We propose…