Search Results for author:
Found 5 papers, 0 papers with code
Full-attention based Neural Architecture Search using Context Auto-regression
Thus, it is appropriate to consider using NAS methods to discover a better self-attention architecture automatically.
Generating Adjacency Matrix for Video Relocalization
In this paper, we continue our work on video relocalization task.
Graph Neural Network for Video Relocalization
In this paper, we focus on video relocalization task, which uses a query video clip as input to retrieve a semantic relative video clip in another untrimmed long video.
Soft-Root-Sign Activation Function
At present, the most effective and widely-used activation function is ReLU.
Comb Convolution for Efficient Convolutional Architecture
Convolutional neural networks (CNNs) are inherently suffering from massively redundant computation (FLOPs) due to the dense connection pattern between feature maps and convolution kernels.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
