Abstract: Label Distribution Learning (LDL) is an effective approach for handling label ambiguity, as it can analyze all labels at once and indicate the extent to which each label describes a given ...

This repository is the implementation of the paper: Jingwei Qu, Pingshun Zhang, Enyu Che, Yinan Chen, and Haibin Ling. Graph Transformer for Label Placement. TVCG, 2025. It contains the training and ...

Abstract: Multi-label image recognition aims to predict a set of labels that present in an image. The key to deal with such problem is to mine the associations between image contents and labels, and ...