David J. Crandall

video understanding (4) weakly supervised learning (3) zero-shot learning (3) metric learning (2) egocentric vision (2) activity recognition (2) neural network (2) video object segmentation (2) convolutional neural network (2) graph neural network (2) multimodal learning (2) egocentric video (2) depth estimation (1) audio-visual learning (1) point cloud (1) semantic segmentation (1) representation learning (1) hand pose estimation (1) attention mechanism (1) person re-identification (1)