Chao Zheng

autonomous driving (4) 3d lane detection (3) adversarial text attack (2) weakly supervised learning (2) scene understanding (1) embedding learning (1) contrastive learning (1) self-supervised learning (1) action recognition (1) video classification (1) question answering (1) multimodal learning (1) lane detection (1) trajectory prediction (1) point cloud (1) model robustness (1) video understanding (1) human pose estimation (1) cross-modal retrieval (1) semantic segmentation (1)