Video Semantic Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

8 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 418 papers with code (895 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Pyramid Scene Parsing Network
  4 Dec 2016 67 repositories listed Syntology ran 7 of 29 samples · 22 unverified · 5 pointer-only (licence)
  Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
• Fully Convolutional Networks for Semantic Segmentation
  20 May 2016 37 repositories listed
  Convolutional networks are powerful visual models that yield hierarchies of features.
• SAM 2: Segment Anything in Images and Videos
  1 Aug 2024 11 repositories listed Syntology ran 28 of 49 samples · 21 unverified
  We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos.
• Mask2Former for Video Instance Segmentation
  20 Dec 2021 6 repositories listed Syntology ran 2 of 7 samples · 5 unverified
  We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline.
• Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective
  31 Mar 2021 5 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning.
• Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
  14 Mar 2021 5 repositories listed Syntology ran 9 of 18 samples · 9 unverified
  We present Modular interactive VOS (MiVOS) framework which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance.
• PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
  24 Jul 2018 5 repositories listed Syntology ran 3 of 15 samples · 12 unverified · 3 pointer-only (licence)
  We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations.
• GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation
  20 Sep 2023 4 repositories listed
  This paper studies the unsupervised domain adaption (UDA) for echocardiogram video segmentation, where the goal is to generalize the model trained on the source domain to other unlabelled target domains.
• Make One-Shot Video Object Segmentation Efficient Again
  3 Dec 2020 4 repositories listed
  In the semi-supervised setting, the first mask of each object is provided at test time.
• Interactive Video Object Segmentation Using Global and Local Transfer Modules
  16 Jul 2020 4 repositories listed Syntology ran 0 of 15 samples · 15 unverified
  The global transfer module conveys the segmentation information in an annotated frame to a target frame, while the local transfer module propagates the segmentation information in a temporally adjacent frame to the…
• CCNet: Criss-Cross Attention for Semantic Segmentation
  28 Nov 2018 4 repositories listed Syntology ran 9 of 14 samples · 5 unverified
  Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage.
• YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
  3 Sep 2018 4 repositories listed
  End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i.
• Lucid Data Dreaming for Video Object Segmentation
  28 Mar 2017 4 repositories listed
  Our approach is suitable for both single and multiple object segmentation.
• DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
  29 Mar 2024 3 repositories listed Syntology ran 1 of 5 samples · 4 unverified · 3 pointer-only (licence)
  Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient…
• Segment Everything Everywhere All at Once
  13 Apr 2023 3 repositories listed
  In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).
• SegGPT: Segmenting Everything In Context
  6 Apr 2023 3 repositories listed Syntology ran 6 of 10 samples · 4 unverified
  We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images.
• EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
  26 Sep 2022 3 repositories listed Syntology ran 7 of 7 samples · 0 unverified · 7 pointer-only (licence)
  VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets.
• Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
  9 Jun 2021 3 repositories listed Syntology ran 6 of 10 samples · 4 unverified · 2 pointer-only (licence)
  This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation.
• Physarum Powered Differentiable Linear Programming Layers and Applications
  30 Apr 2020 3 repositories listed
  We describe our development and show the use of our solver in a video segmentation task and meta-learning for few-shot learning.
• Video Object Segmentation using Space-Time Memory Networks
  1 Apr 2019 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory.
• FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
  25 Feb 2019 3 repositories listed Syntology ran 1 of 9 samples · 8 unverified
  Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use.
• UAVid: A Semantic Segmentation Dataset for UAV Imagery
  24 Oct 2018 3 repositories listed
  There already exist several semantic segmentation datasets for comparison among semantic segmentation methods in complex urban scenes, such as the Cityscapes and CamVid datasets, where the side views of the objects are…
• Video Object Segmentation with Re-identification
  1 Aug 2017 3 repositories listed
  Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.
• Deep Feature Flow for Video Recognition
  23 Nov 2016 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.
• Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
  3 May 2025 2 repositories listed
  Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process.
• Stable Mean Teacher for Semi-supervised Video Action Detection
  10 Dec 2024 2 repositories listed Syntology ran 2 of 6 samples · 4 unverified
  In this work, we focus on semi-supervised learning for video action detection.
• Underwater Camouflaged Object Tracking Meets Vision-Language SAM2
  25 Sep 2024 2 repositories listed
  To bridge this gap, we take a step forward by proposing the first large-scale multi-modal underwater camouflaged object tracking dataset, namely UW-COT220.
• VISA: Reasoning Video Object Segmentation via Large Language Models
  16 Jul 2024 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS).
• PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
  24 Jun 2024 2 repositories listed
  Moreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments.
• UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
  25 Dec 2023 2 repositories listed Syntology ran 9 of 9 samples · 0 unverified
  We evaluate our unified models on various benchmarks.

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.