In this work, we construct a large-scale dataset for Ground-to-Aerial Pe...
This paper makes the first attempt to tackle the challenging task of
rec...
Compositional Zero-Shot Learning (CZSL) aims to train models to recogniz...
Images captured by rolling shutter (RS) cameras under fast camera motion...
Non-exemplar class-incremental learning refers to classifying new and ol...
To imitate the ability of keeping learning of human, continual learning ...
Multispectral pedestrian detection is an important task for many
around-...
With the emergence of large pre-trained vison-language model like CLIP,
...
With the explosive growth of video data, video summarization, which atte...
Because of the invisible human keypoints in images caused by illuminatio...
In the last two decades, scholars have designed various types of
bibliog...
The creative process is essentially Darwinian and only a small proportio...