3D scene reconstruction from 2D images has been a long-standing task. In...
One-shot Neural architecture search (One-shot NAS) has been proposed as ...
Large pre-trained models (LPMs), such as LLaMA and ViT-G, have shown
exc...
The combination of LiDAR and camera modalities is proven to be necessary...
Oriented bounding box regression is crucial for oriented object detectio...
Robot navigation in dynamic environments shared with humans is an import...
Classification methods for binary (yes/no) tasks often produce a continu...
In recent years, neural architecture search (NAS) has shown great
compet...
Accurate rail location is a crucial part in the railway support driving
...
Knowledge distillation has made remarkable achievements in model compres...
To solve the coupling problem of control loops and the adaptive paramete...
Adequate labeled data and expensive compute resources are the prerequisi...
In the past years, significant improvements in the field of neural
archi...
Pedestrian attribute recognition in surveillance scenarios is still a
ch...
Proportional-integral-derivative (PID) control is the most widely used i...
Machine learning practitioners often compare the results of different
cl...
In database systems, index is the key component to support efficient sea...
Previous AutoML pruning works utilized individual layer features to
auto...