Papers › Video Object Segmentation with Language Referring Expressions

Video Object Segmentation with Language Referring Expressions

21 Mar 2018arXiv:1803.08006archive 2025-07-28

Anna Khoreva, Anna Rohrbach, Bernt Schiele

Most state-of-the-art semi-supervised video object segmentation methods rely on a pixel-accurate mask of a target object provided for the first frame of a video. However, obtaining a detailed segmentation mask is expensive and time-consuming. In this work we explore an alternative way of identifying a target object, namely by employing language referring expressions. Besides being a more practical and natural way of pointing out a target object, using language specifications can help to avoid drift as well as make the system more robust to complex dynamics and appearance variations. Leveraging recent advances of language grounding models designed for images, we propose an approach to extend them to video data, ensuring temporally coherent predictions. To evaluate our method we augment the popular video object segmentation benchmarks, DAVIS'16 and DAVIS'17 with language descriptions of target objects. We show that our language-supervised approach performs on par with the methods which have access to a pixel-level mask of the target object on DAVIS'16 and is competitive to methods using scribbles on the challenging DAVIS'17 dataset.

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

ObjectReferring Expression SegmentationSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Datasets

Introduced by this paper, per the archive.

Referring Expressions for DAVIS 2016 & 2017

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation DAVIS 2017 (val) Khoreva et al. J&F 1st frame 39.3 #16 of 18 Archive leaderboard report
Referring Expression Segmentation DAVIS 2017 (val) Khoreva et al. J&F Full video 37.1 #16 of 18 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 VOSwL F-measure (Decay) 8.6 #54 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 VOSwL F-measure (Mean) 84.2 #54 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 VOSwL F-measure (Recall) 93.9 #54 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 VOSwL J&F 83.65 #54 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 VOSwL Jaccard (Decay) 6.9 #54 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 VOSwL Jaccard (Mean) 83.1 #54 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 VOSwL Jaccard (Recall) 95.7 #54 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) VOSwL (Language) J&F 60.8 #71 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) VOSwL (Language) Jaccard (Mean) 58.0 #71 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) VOSwL F-measure (Decay) 24.5 #81 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) VOSwL F-measure (Mean) 63.5 #81 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) VOSwL F-measure (Recall) 70.4 #81 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) VOSwL Jaccard (Decay) 22.4 #81 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) VOSwL Jaccard (Recall) 66.1 #81 of 81 Archive leaderboard report
Video Object Segmentation DAVIS 2016 VOSwL (Mask+Language) mIoU 84.5 #21 of 24 Archive leaderboard report
Video Object Segmentation DAVIS 2016 VOSwL (Language) mIoU 82.8 #22 of 24 Archive leaderboard report
Video Object Segmentation DAVIS 2017 VOSwL (Mask+Language) J&F 62.2 #3 of 5 Archive leaderboard report
Video Object Segmentation DAVIS 2017 VOSwL (Mask+Language) mIoU 59 #3 of 5 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