Papers › AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation

AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation

1 Oct 2019ICCV 2019 10archive 2025-07-28

Huaijia Lin, Xiaojuan Qi, Jiaya Jia

Most video object segmentation approaches process objects separately. This incurs high computational cost when multiple objects exist. In this paper, we propose AGSS-VOS to segment multiple objects in one feed-forward path via instance-agnostic and instance-specific modules. Information from the two modules is fused via an attention-guided decoder to simultaneously segment all object instances in one path. The whole framework is end-to-end trainable with instance IoU loss. Experimental results on Youtube- VOS and DAVIS-2017 dataset demonstrate that AGSS-VOS achieves competitive results in terms of both accuracy and efficiency.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

DecoderObjectOne-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) AGSS-VOS D17 test (F) 59.7 #22 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) AGSS-VOS D17 test (G) 57.2 #22 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) AGSS-VOS D17 test (J) 54.8 #22 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) AGSS-VOS D17 val (F) 69.9 #22 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) AGSS-VOS D17 val (G) 67.4 #22 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) AGSS-VOS D17 val (J) 64.9 #22 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) AGSS-VOS FPS 10.0 #22 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) AGSS-VOS F-measure (Mean) 69.8 #65 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) AGSS-VOS J&F 66.6 #65 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) AGSS-VOS Jaccard (Mean) 63.4 #65 of 81 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.

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