Hongzhou Wu — accepted AI-conference papers

2025

TFS: Revisiting Temporal Language Grounding from Frequency Spiking Perspective

Yifan Lyu, Hongzhou Wu, Lixiang Liu, Chuxiong Sun

ICASSP 2025accepted

Temporal Language Grounding (TLG) aims to localize moments in untrimmed videos that are most relevant to natural language queries. While existing weakly-supervised methods have achieved significant success in exploring cross-modal relationships, they still face a critical bottleneck: the interferenc…

Cited by 0 Source ↗Scholar ↗

2024

MSFR: Stance Detection Based on Multi-Aspect Semantic Feature Representation via Hierarchical Contrastive Learning

Xuechen Zhao, Lei Tian, Feng Xie, Bin Zhou, Haiyang Wang, Hongzhou Wu +1

ICASSP 2024accepted

Zero-shot stance detection aims to determine the stance of previously unseen targets during the inference phase. Achieving effective feature alignment from seen targets to unseen targets is crucial for zero-shot stance detection. In this paper, we propose MSFR, a hierarchical contrastive learning fr…

Cited by 0 Source ↗Scholar ↗