Search Results for author:
Found 3 papers, 2 papers with code
Lightweight Recurrent Cross-modal Encoder for Video Question Answering
Due to the high computational cost of the self-attention and the high dimensional data of video, they either have to settle for: 1) only training the cross-modal encoder on offline-extracted video and text features or 2) training the cross-modal encoder with the video and text feature extractor, but only using sparsely-sampled video frames.
Ranked #7 on
TGIF-Transition
on TGIF-QA
Action knowledge for video captioning with graph neural networks
However, directly using the action features without object-specific representation may not well capture the object interactions.
Ranked #4 on
Video Captioning
on MSVD-CTN
Combining transformer and CNN for object detection in UAV imagery
Combining multiple models is a well-known technique to improve predictive performance in challenging tasks such as object detection in UAV imagery.
