TFS: Revisiting Temporal Language Grounding from Frequency Spiking Perspective
Yifan Lyu, Hongzhou Wu, Lixiang Liu, Chuxiong Sun
Abstract
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 interference of task-irrelevant information in query embeddings. To address this issue, we propose TLG Frequency Spiking (TFS), a dimensional mask derived from the frequency domain that models the varying importance specific to different queries. By enhancing the understanding of queries, TFS effectively optimizes the cross-modal alignment of visual and textual modalities. Experimental results show that TFS significantly outperforms state-of-the-art baselines on both the Charades-STA and ActivityNet-Captions datasets.
BibTeX
@inproceedings{icassp2025_tfsrevisitingtem,
title = {TFS: Revisiting Temporal Language Grounding from Frequency Spiking Perspective},
author = {Yifan Lyu and Hongzhou Wu and Lixiang Liu and Chuxiong Sun},
booktitle = {ICASSP 2025},
year = {2025}
}