Fusion of Short-term and Long-term Attention for Video Mirror Detection

Techniques for detecting mirrors from static images have witnessed rapid growth in recent years. However, these methods detect mirrors from single input images. Detecting mirrors from video requires further consideration of temporal consistency between frames. We observe that humans can recognize mi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-07
Main Authors: Xu, Mingchen, Wu, Jing, Lai, Yukun, Ji, Ze
Format: Article
Language:English
Subjects:
Benchmarks
Datasets
Feature extraction
Frames (data processing)
Modules
Performance evaluation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Techniques for detecting mirrors from static images have witnessed rapid growth in recent years. However, these methods detect mirrors from single input images. Detecting mirrors from video requires further consideration of temporal consistency between frames. We observe that humans can recognize mirror candidates, from just one or two frames, based on their appearance (e.g. shape, color). However, to ensure that the candidate is indeed a mirror (not a picture or a window), we often need to observe more frames for a global view. This observation motivates us to detect mirrors by fusing appearance features extracted from a short-term attention module and context information extracted from a long-term attention module. To evaluate the performance, we build a challenging benchmark dataset of 19,255 frames from 281 videos. Experimental results demonstrate that our method achieves state-of-the-art performance on the benchmark dataset.
ISSN:2331-8422