Composed image retrieval, a task involving the search for a target image...
Few-shot class-incremental learning (FSCIL) aims to continually learn ne...
Most recent works focus on answering first order logical queries to expl...
Recent incremental learning for action recognition usually stores
repres...
The top-k recommendation is a fundamental task in recommendation systems...
Superpixel segmentation has recently seen important progress benefiting ...
We aim to tackle the challenging yet practical scenery image outpainting...
With the rapid development of E-commerce and the increase in the quantit...
Recently, some approaches are proposed to harness deep convolutional net...
Skin lesion segmentation is a crucial step in the computer-aided diagnos...
The outpainting results produced by existing approaches are often too ra...
Crowd scene analysis receives growing attention due to its wide applicat...
Knowledge distillation (KD) is widely used for training a compact model ...
Image-text matching tasks have recently attracted a lot of attention in ...
Relationships, as the bond of isolated entities in images, reflect the
i...
Aggregating deep convolutional features into a global image vector has
a...