Junfu Pu

video understanding (2) sign language recognition (2) connectionist temporal classification (2) weakly supervised learning (1) knowledge distillation (1) sign language translation (1) video sequence (1) dynamic time warping (1) convolutional neural network (1) multimodal large language model (1) image-text retrieval (1) hallucination detection (1) encoder-decoder architecture (1) monolingual datum (1) multimodal hallucination (1) 3d convolutional network (1) 3d convolutional neural network (1) 3d residual network (1) continuous sign language recognition (1) dilated convolutional network (1)