![]() I will discuss the principles of view construction for contrastive learning, how the vanilla contrastive learning objective loses temporal information, and how to fix it. The first part of the talk focuses on recognition, where the goal is to learn temporally aware visual representations via self-supervised learning. In this talk, I will introduce several recent works on learning rich semantic and dynamic information from unlabeled videos. These tasks are often too rich to be discretized into categorical labels, or too ambiguous to be manually labeled by humans, making standard supervised deep learning unfit for the tasks. To transfer such success to our daily life, we still need to develop machine intelligence that recognizes hierarchical, composite human activities, and predicts how events unfold over time. Deep learning has brought tremendous progress to visual recognition, thanks to big labeled data and fast compute.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |