Specifically, we replace the MLP module in the token-mixing step with a novel sparse MLP (sMLP) module.
Ranked #131 on Image Classification on ImageNet
The proxy task is to estimate the position and size of the image patch in a sequence of video frames, given only the target bounding box in the first frame.
Generally, model update is formulated as an online learning problem where a target model is learned over the online training set.
Ranked #1 on Visual Tracking on OTB-2013