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

arXiv: https://arxiv.org/abs/2407.07999 · HTML: https://mlsanity.com/paper/2407.07999/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 13 of 13)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [YouTube-VOS: Sequence-to-Sequence Video Object Segmentation](https://mlsanity.com/paper/1809.00461/) (2018)
- [Reconstructing 3D Human Pose by Watching Humans in the Mirror](https://mlsanity.com/paper/2104.00340/) (2021)
- [Triple-cooperative Video Shadow Detection](https://mlsanity.com/paper/2103.06533/) (2021)
- [SCOTCH and SODA: A Transformer Video Shadow Detection Framework](https://mlsanity.com/paper/2211.06885/) (2022)
- [Mirror3D: Depth Refinement for Mirror Surfaces](https://mlsanity.com/paper/2106.06629/) (2021)
- [Efficient Mirror Detection via Multi-level Heterogeneous Learning](https://mlsanity.com/paper/2211.15644/) (2022)
- [Symmetry-Aware Transformer-based Mirror Detection](https://mlsanity.com/paper/2207.06332/) (2022)

## Abstract (arXiv)

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.