sign language video understanding
2017 – Present
deep learning, generative modeling
2016 – Present
deep learning, multimodal, cross-modal
2015 – Present
visual grounding
2019 – 2021
deep learning, unsupervised representation learning, self-supervised representation learning
2017 – 2021
deep learning, video
2016 – 2021
deep learning, computer vision, instance segmentation
2015 – 2020
adaptive computation time
2017 – 2019
deep learning, saliency prediction, gaze prediction
2015 – 2019