Transformers have achieved great success in many artificial intelligence fields, such as
natural language processing, computer vision, and audio processing. Therefore, it is natural …

Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

Transformer models have shown great success handling long-range interactions, making
them a promising tool for modeling video. However, they lack inductive biases and scale …

Text-video retrieval is a fundamental task with high practical value in multi-modal research.
Inspired by the great success of pre-trained image-text models with large-scale data, such …

We propose a novel deep neural network architecture to learn interpretable representation
for medical image analysis. Our architecture generates a global attention for region of …

Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One
reason is that existing robustness benchmarks are limited, as they either rely on synthetic …

Video copy localization aims to precisely localize all the copied segments within a pair of
untrimmed videos in video retrieval applications. Previous methods typically start from frame …

Effective learning of spatial-temporal information within a point cloud sequence is highly
important for many down-stream tasks such as 4D semantic segmentation and 3D action …

Due to the computational complexity of self-attention (SA), prevalent techniques for image
deblurring often resort to either adopting localized SA or employing coarse-grained global …