Jie Lei

multimodal learning (12) video understanding (7) video question answering (6) video captioning (4) temporal modeling (3) adversarial learning (3) text-to-video retrieval (3) object detection (3) neural network (3) self-supervised learning (3) deepfake detection (2) unsupervised learning (2) few-shot learning (2) vision transformer (2) video retrieval (2) deep learning (2) model compression (2) image captioning (2) transformer architecture (2) zero-shot learning (2)