Papers › Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation

Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation

10 Dec 2020arXiv:2012.05499archive 2025-07-28

Daizong Liu, Shuangjie Xu, Xiao-Yang Liu, Zichuan Xu, Wei Wei, Pan Zhou

This paper addresses the task of segmenting class-agnostic objects in semi-supervised setting. Although previous detection based methods achieve relatively good performance, these approaches extract the best proposal by a greedy strategy, which may lose the local patch details outside the chosen candidate. In this paper, we propose a novel spatiotemporal graph neural network (STG-Net) to reconstruct more accurate masks for video object segmentation, which captures the local contexts by utilizing all proposals. In the spatial graph, we treat object proposals of a frame as nodes and represent their correlations with an edge weight strategy for mask context aggregation. To capture temporal information from previous frames, we use a memory network to refine the mask of current frame by retrieving historic masks in a temporal graph. The joint use of both local patch details and temporal relationships allow us to better address the challenges such as object occlusion and missing. Without online learning and fine-tuning, our STG-Net achieves state-of-the-art performance on four large benchmarks (DAVIS, YouTube-VOS, SegTrack-v2, and YouTube-Objects), demonstrating the effectiveness of the proposed approach.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph Neural NetworkObjectOne-shot visual object segmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D16 val (F) 86.0 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D16 val (G) 85.7 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D16 val (J) 85.4 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D17 test (F) 66.5 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D17 test (G) 63.1 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D17 test (J) 59.7 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D17 val (F) 77.9 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D17 val (G) 74.7 #11 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) STG-Net D17 val (J) 71.5 #11 of 26 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Graph Neural NetworkMemory Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections