Search Results for author:
Found 3 papers, 0 papers with code
AE-Net:Adjoint Enhancement Network for Efficient Action Recognition in Video Understanding
Action recognition in video understanding is a challenging task, largely because of the complexity and difficulty in temporal modeling, making it suffer from motion information loss and misalignment of temporal attention in spatial dimensions.
Ranked #28 on
Action Recognition
on Something-Something V1
Guidance Module Network for Video Captioning
In this paper, we present a novel architecture which introduces a guidance module to encourage the encoder-decoder model to generate words related to the past and future words in a caption.
Attention to Head Locations for Crowd Counting
Occlusions, complex backgrounds, scale variations and non-uniform distributions present great challenges for crowd counting in practical applications.
