Zhenyu He

object tracking (5) visual tracking (4) multimodal learning (3) convolutional neural network (2) visual grounding (2) semantic segmentation (2) action recognition (1) feature learning (1) image segmentation (1) label propagation (1) motion synthesis (1) attention mechanism (1) knowledge transfer (1) image fusion (1) compressive sensing (1) multi-task learning (1) cross-modal learning (1) ensemble learning (1) image reconstruction (1) text generation (1)