Recently, a variety of methods under the name of non-contrastive learnin...
Steerable models can provide very general and flexible equivariance by
f...
Representing text as graph to solve the summarization task has been disc...
Nowadays, E-commerce is increasingly integrated into our daily lives.
Me...
With the increasing scale and diversification of interaction behaviors i...
Hashing has been widely used in approximate nearest neighbor search for ...
Spherical signals exist in many applications, e.g., planetary data, LiDA...
Recent research has shown that incorporating equivariance into neural ne...
Extracting effective deep features to represent content and style inform...
Graph neural networks (GNNs) achieve remarkable performance for tasks on...
Images or videos always contain multiple objects or actions. Multi-label...
Sparsity is regarded as a desirable property of representations, especia...
Universal style transfer is an image editing task that renders an input
...
Neural Architecture Search (NAS) has been widely studied for designing
d...
Existing neural models for dialogue response generation assume that
utte...
In this paper, we propose a novel non-convex tensor rank surrogate funct...
Fashion landmark detection is a challenging task even using the current ...
Recent studies on face attribute transfer have achieved great success,
e...
Understanding the generalization of deep learning has raised lots of con...
Disentangling factors of variation has always been a challenging problem...