End-to-end learning of visual representations from uncurated instructional videos

Annotating videos is cumbersome, expensive and not scalable. Yet, many strong video models still rely on manually annotated data. With the recent introduction of the HowTo100M dataset, narrated videos now offer the possibility of learning video representations without manual supervision. In this wor...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: Miech, A, Alayrac, J-B, Smaira, L, Laptev, I, Sivic, J, Zisserman, A
Định dạng: Conference item
Ngôn ngữ:English
Được phát hành: IEEE 2020