In contrast to the abundant research focusing on large-scale models, the...
Self-supervised representation learning (SSRL) has gained increasing
att...
Semantic segmentation has recently achieved notable advances by exploiti...
The existing deep learning models suffer from out-of-distribution (o.o.d...
Recent segmentation methods, such as OCR and CPNet, utilizing "class lev...
The latest trend in the bottom-up perspective for arbitrary-shape scene ...
Self-attention and channel attention, modelling the semantic
interdepend...
Crowd counting, i.e., estimating the number of people in a crowded area,...
The state-of-the-art semantic segmentation solutions usually leverage
di...
Scene text recognition has recently been widely treated as a
sequence-to...
Counting people or objects with significantly varying scales and densiti...
Crowd counting, for estimating the number of people in a crowd using
vis...
Crowd counting, for estimating the number of people in a crowd using
vis...
Tiny face detection aims to find faces with high degrees of variability ...
Text in an image provides vital information for interpreting its content...