← Search

Juncheng Zhou

2 accepted papers

2025

A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification

COLING 2025main

Hierarchical text classification (HTC) is an important task in natural language processing (NLP). Existing methods typically utilize both text features and the hierarchical structure of labels to categorize text effectively. However, these approaches often struggle with fine-grained labels, which ar…

Cited by 2SourcePDFScholar
2025

Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image Restoration

ICCV 2025poster

Transformer-based approaches have gained significant attention in image restoration, where the core component, i.e, Multi-Head Attention (MHA), plays a crucial role in capturing diverse features and recovering high-quality results. In MHA, heads perform attention calculation independently from unifo…