yuxin mao

multimodal learning (3) motion estimation (3) optical flow (2) multi-modal learning (2) attention mechanism (2) audio-visual segmentation (2) audio-visual event localization (2) event camera (1) cross-modal learning (1) semantic segmentation (1) audio-visual learning (1) trajectory prediction (1) image reconstruction (1) point cloud (1) vision transformer (1) weakly-supervised learning (1) cross-modal representation (1) joint learning (1) video understanding (1) image segmentation (1)