Position embedding fusion on transformer for dense video captioning

von Yang, Sixuan
Veröffentlicht in International FLINS Conference (14. : Köln : 2020) Developments of artificial intelligence technologies in computation and robotics (2020)

Smoothing CNN for end-to-end training in visual question answering

von Long, Yu
Veröffentlicht in International FLINS Conference (14. : Köln : 2020) Developments of artificial intelligence technologies in computation and robotics (2020)