# Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation

Source: [Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation](<https://www.sota2.com/research/paper/68fa71411e209131cea502bf>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:01:40.608Z

Authors: Ping Li, Yu Zhang, Li Yuan, Huaxin Xiao, Binbin Lin, Xianghua Xu

Published: 2023-09-21T01:09:46.000Z

## Abstract

Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not fully use spatial-temporal context and fail to tackle this challenging task in real-time. This motivates us to develop an efficient Long-Short Temporal Attention network (termed LSTA) for unsupervised VOS task from a holistic view. Specifically, LSTA consists of two dominant modules, i.e., Long Temporal Memory and Short Temporal Attention. The former captures the long-term global pixel relations of the past frames and the current frame, which models constantly present objects by encoding appearance pattern. Meanwhile, the latter reveals the short-term local pixel relations of one nearby frame and the current frame, which models moving objects by encoding motion pattern. To speedup the inference, the efficient projection and the locality-based sliding window are adopted to achieve nearly linear time complexity for the two light modules, respectively. Extensive empirical studies on several benchmarks have demonstrated promising performances of the proposed method with high efficiency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [RGB-D Video Salient Object Detection on DViSal](<https://www.sota2.com/research/sota/rgb-d-video-salient-object-detection-on-dvisal.md>): RGB-D Video Salient Object Detection; DVisal; S\_alpha: 70.

- [RGB-D Video Salient Object Detection on RDVS](<https://www.sota2.com/research/sota/rgb-d-video-salient-object-detection-on-rdvs.md>): RGB-D Video Salient Object Detection; RDVS; S\_alpha: 65.

- [RGB-D Video Salient Object Detection on ViDSOD-100](<https://www.sota2.com/research/sota/rgb-d-video-salient-object-detection-on-vidsod-100.md>): RGB-D Video Salient Object Detection; ViDSOD-100; S\_alpha: 67.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.11707>)

[PDF](<https://arxiv.org/pdf/2309.11707.pdf>)