Human-Object Interaction (HOI) detection aims to understand the interact...
Prompt tuning is a parameter-efficient way to deploy large-scale pre-tra...
Interactive image segmentation enables annotators to efficiently perform...
Text-driven 3D stylization is a complex and crucial task in the fields o...
Parameter-efficient transfer learning (PETL) is an emerging research spo...
Few-shot learning problem focuses on recognizing unseen classes given a ...
Pseudo-label-based semi-supervised learning (SSL) has achieved great suc...
In this paper, we discover two factors that inhibit POMs from achieving ...
Weakly supervised object localization (WSOL) aims to learn object locali...
To bridge the ever increasing gap between deep neural networks' complexi...