The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Yurui, Yang, Yang, Chen, Shou, Wu, Xiangyu, Chen, Qingguo, Lu, Jianfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914855955464192
author Huang, Yurui
Yang, Yang
Chen, Shou
Wu, Xiangyu
Chen, Qingguo
Lu, Jianfeng
author_facet Huang, Yurui
Yang, Yang
Chen, Shou
Wu, Xiangyu
Chen, Qingguo
Lu, Jianfeng
contents In this paper, we propose a solution for improving the quality of temporal sound localization. We employ a multimodal fusion approach to combine visual and audio features. High-quality visual features are extracted using a state-of-the-art self-supervised pre-training network, resulting in efficient video feature representations. At the same time, audio features serve as complementary information to help the model better localize the start and end of sounds. The fused features are trained in a multi-scale Transformer for training. In the final test dataset, we achieved a mean average precision (mAP) of 0.33, obtaining the second-best performance in this track.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02318
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023
Huang, Yurui
Yang, Yang
Chen, Shou
Wu, Xiangyu
Chen, Qingguo
Lu, Jianfeng
Sound
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
In this paper, we propose a solution for improving the quality of temporal sound localization. We employ a multimodal fusion approach to combine visual and audio features. High-quality visual features are extracted using a state-of-the-art self-supervised pre-training network, resulting in efficient video feature representations. At the same time, audio features serve as complementary information to help the model better localize the start and end of sounds. The fused features are trained in a multi-scale Transformer for training. In the final test dataset, we achieved a mean average precision (mAP) of 0.33, obtaining the second-best performance in this track.
title The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023
topic Sound
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2407.02318