Video Instance Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 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

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 94 papers with code (148 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.

• Simple Online and Realtime Tracking with a Deep Association Metric
  21 Mar 2017 75 repositories listed Syntology ran 12 of 40 samples · 28 unverified · 7 pointer-only (licence)
  Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
• 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.
• Video Instance Segmentation
  12 May 2019 6 repositories listed Syntology ran 3 of 11 samples · 8 unverified · 1 pointer-only (licence)
  The goal of this new task is simultaneous detection, segmentation and tracking of instances in videos.
• Instances as Queries
  5 May 2021 5 repositories listed Syntology ran 1 of 3 samples · 2 unverified
  The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the…
• 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…
• Temporally Efficient Vision Transformer for Video Instance Segmentation
  18 Apr 2022 3 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS).
• InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
  22 Mar 2024 2 repositories listed
  We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue.
• Spatio-temporal Prompting Network for Robust Video Feature Extraction
  4 Feb 2024 2 repositories listed
  Then, these video prompts are prepended to the patch embeddings of the current frame as the updated input for video feature extraction.
• MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training
  3 Aug 2022 2 repositories listed
  By only training a query-based image instance segmentation model, MinVIS outperforms the previous best result on the challenging Occluded VIS dataset by over 10% AP.
• In Defense of Online Models for Video Instance Segmentation
  21 Jul 2022 2 repositories listed Syntology ran 3 of 5 samples · 2 unverified
  In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance.
• RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
  8 Mar 2022 2 repositories listed Syntology ran 2 of 11 samples · 9 unverified
  Given an input image or video, our framework first conducts multi-label classification over the complete label, then sorts the complete label and selects a small subset according to their class confidence scores.
• SeqFormer: Sequential Transformer for Video Instance Segmentation
  15 Dec 2021 2 repositories listed
  Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently.
• D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
  15 Nov 2021 2 repositories listed
  We further show that D2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
• UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution
  22 Oct 2021 2 repositories listed
  In this report, we introduce our (pretty straightforard) two-step "detect-then-match" video instance segmentation method.
• Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
  10 Jun 2021 2 repositories listed
  Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection.
• Occluded Video Instance Segmentation: A Benchmark
  2 Feb 2021 2 repositories listed
  On the OVIS dataset, the highest AP achieved by state-of-the-art algorithms is only 16.
• End-to-End Video Instance Segmentation with Transformers
  30 Nov 2020 2 repositories listed
  Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.
• ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts
  24 May 2025 1 repository listed
  Reasoning Video Object Segmentation is a challenging task, which generates a mask sequence from an input video and an implicit, complex text query.
• SyncVIS: Synchronized Video Instance Segmentation
  1 Dec 2024 1 repository listed
  Recent DETR-based methods have advanced the development of Video Instance Segmentation (VIS) through transformers' efficiency and capability in modeling spatial and temporal information.
• Foundation Models for Amodal Video Instance Segmentation in Automated Driving
  21 Sep 2024 1 repository listed
  This way, while basing our method on an amodal instance segmentation, we nevertheless obtain video-level amodal instance segmentation results.
• MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice
  5 Sep 2024 1 repository listed
  To this end, we introduce: (i) a new task termed \emph{space-time instance segmentation}, similar to video instance segmentation, whose goal is to segment instances throughout the entire duration of the sensor input…
• Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency
  29 Aug 2024 1 repository listed
  This method is based on two key innovations: a Temporal Eigenvalue Loss (TEL) and a clip-level Quality Cluster Coefficient (QCC).
• Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation
  10 Jul 2024 1 repository listed
  We discover that the domain gap between the VLM features (e.
• Context-Aware Video Instance Segmentation
  3 Jul 2024 1 repository listed
  In this paper, we introduce the Context-Aware Video Instance Segmentation (CAVIS), a novel framework designed to enhance instance association by integrating contextual information adjacent to each object.
• PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation
  28 Jun 2024 1 repository listed
  This method achieves high video instance segmentation performance without manual video annotations, offering a cost-effective solution and new perspectives for video instance segmentation applications.
• CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation
  19 Mar 2024 1 repository listed
  The experiments are performed on various video instance segmentation datasets, which demonstrate the effectiveness of our proposed method, especially for novel categories.
• UniVS: Unified and Universal Video Segmentation with Prompts as Queries
  28 Feb 2024 1 repository listed Syntology ran 12 of 14 samples · 2 unverified · 14 pointer-only (licence)
  Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge.
• TDViT: Temporal Dilated Video Transformer for Dense Video Tasks
  14 Feb 2024 1 repository listed
  Deep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i.
• Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation
  18 Jan 2024 1 repository listed
  To mold instance queries to follow Brownian bridge and accomplish alignment with class texts, we design Bridge-Text Alignment (BTA) to learn discriminative bridge-level representations of instances via contrastive…
• DVIS++: Improved Decoupled Framework for Universal Video Segmentation
  20 Dec 2023 1 repository listed
  We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video…

Syntology lines on 9 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.