Recently, efficient fine-tuning of large-scale pre-trained models has
at...
Few-shot classification is a challenging problem as only very few traini...
For video recognition task, a global representation summarizing the whol...
Weakly-supervised object detection (WSOD) has emerged as an inspiring re...
To promote the developments of object detection, tracking and counting
a...
Recently the vision transformer (ViT) architecture, where the backbone p...
Recent works have demonstrated that global covariance pooling (GCP) has ...
This paper proposes a space-time multi-scale attention network (STANet) ...
Channel attention has recently demonstrated to offer great potential in
...
Blind deconvolution is a classical yet challenging low-level vision prob...
Collection of massive well-annotated samples is effective in improving o...
Compared with global average pooling in existing deep convolutional neur...
Deep Convolutional Networks (ConvNets) are fundamental to, besides
large...
Deep Convolutional Networks (ConvNets) are fundamental to, besides
large...
Although Faster R-CNN and its variants have shown promising performance ...
Global covariance pooling in Convolutional neural neworks has achieved
i...
By stacking layers of convolution and nonlinearity, convolutional networ...
The bag-of-features (BoF) model for image classification has been thorou...