3D multi-object tracking (MOT) is vital for many applications including
...
We introduce VideoFlow, a novel optical flow estimation framework for vi...
FlowFormer introduces a transformer architecture into optical flow estim...
Physics-informed neural networks (PINNs) have attracted significant atte...
In knowledge distillation, a student model is trained with supervisions ...
Overconfidence has been shown to impair generalization and calibration o...
We tackle the problem of estimating correspondences from a general marke...
In various learning-based image restoration tasks, such as image denoisi...
In this report, we describe the technical details of our submission for ...
Accurate and reliable 3D detection is vital for many applications includ...
We introduce Optical Flow TransFormer (FlowFormer), a transformer-based
...
There are plenty of applications and analysis for time-independent ellip...
We develop a deep learning approach to extract ray directions at discret...
Distributed stochastic gradient descent (SGD) algorithms are widely depl...