# Learning Spatial-Semantic Features for Robust Video Object Segmentation

Source: [Learning Spatial-Semantic Features for Robust Video Object Segmentation](<https://www.sota2.com/research/paper/68fa77da1e209131cea75944>)

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

Data updated: 2025-10-28T13:57:15.327Z

Authors: Xin Li, Deshui Miao, Zhenyu He, Yaowei Wang, Huchuan Lu, Ming-Hsuan Yang

Published: 2024-07-10T15:36:00.000Z

## Abstract

Tracking and segmenting multiple similar objects with distinct or complex parts in long-term videos is particularly challenging due to the ambiguity in identifying target components and the confusion caused by occlusion, background clutter, and changes in appearance or environment over time. In this paper, we propose a robust video object segmentation framework that learns spatial-semantic features and discriminative object queries to address the above issues. Specifically, we construct a spatial-semantic block comprising a semantic embedding component and a spatial dependency modeling part for associating global semantic features and local spatial features, providing a comprehensive target representation. In addition, we develop a masked cross-attention module to generate object queries that focus on the most discriminative parts of target objects during query propagation, alleviating noise accumulation to ensure effective long-term query propagation. Extensive experimental results show that the proposed method achieves state-of-the-art performance on benchmark data sets, including the DAVIS2017 test (\\textbf{87.8\\%}), YoutubeVOS 2019 (\\textbf{88.1\\%}), MOSE val (\\textbf{74.0\\%}), and LVOS test (\\textbf{73.0\\%}), and demonstrate the effectiveness and generalization capacity of our model. The source code and trained models are released at \\href{https://github.com/yahooo-m/S3}{https://github.com/yahooo-m/S3}.

## 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.

- [Long-term Visual Object Tracking and Segmentation on VOTS24](<https://www.sota2.com/research/sota/long-term-visual-object-tracking-and-segmentation-on-vots24.md>): Long-term Visual Object Tracking and Segmentation; VOTS24; Quality (Q): 72.2.

- [Visual Object Tracking on VOT 2024 (test)](<https://www.sota2.com/research/sota/visual-object-tracking-on-vot-2024-test.md>): Visual Object Tracking; VOT 2024 (test); Quality: 72.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.07760>)

[PDF](<https://arxiv.org/pdf/2407.07760.pdf>)
