Research map / Video / Video segmentation and tracking
Video semantic and panoptic segmentation
Segments video frames through flow propagation, mask propagation and unified kernel baselines.
67 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Video segmentation and tracking, keyword cluster “object segmentation · video object · vos”
State History Benchmarks Tried Checklist Preprints Who Export
Where it stands
Few recent reports The tracked benchmarks have at most one report from 2025–26 that could beat the old record, too few to say whether they are still moving.
15 papers in 2023–24 and 21 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 3.4% to 3.9%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Bilateral Space Video Segmentation (CVPR 2016 · 231 citations)
- 2017 · Video Propagation Networks (CVPR 2017 · 240 citations)
- 2018 · Semantic Video Segmentation by Gated Recurrent Flow Propagation (CVPR 2018 · 223 citations)
- 2019 · Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video (CVPR 2019 · 143 citations)
- 2020 · Temporally Distributed Networks for Fast Video Semantic Segmentation (CVPR 2020 · 212 citations)
- 2021 · Spatial Feature Calibration and Temporal Fusion for Effective One-Stage Video Instance Segmentation (CVPR 2021 · 48 citations)
- 2022 · Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation (CVPR 2022 · 79 citations)
- 2023 · TarViS: A Unified Approach for Target-Based Video Segmentation (CVPR 2023 · 38 citations)
- 2024 · Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation (CVPR 2024 · 14 citations)
- 2025 · MatAnyone: Stable Video Matting with Consistent Memory Propagation (CVPR 2025 · 10 citations)
- 2026 · VPSentry: Semi-supervised Video Polyp Segmentation via Sentry-guided Long-term Prototype Fusion with Correlation Dynamic Propagation (AAAI 2026 · 1 citation)
Earliest papers here
- Bilateral Space Video Segmentation (CVPR 2016 · 231 citations)
- Feature Space Optimization for Semantic Video Segmentation (CVPR 2016 · 194 citations)
- Coherent Parametric Contours for Interactive Video Object Segmentation (CVPR 2016 · 23 citations)
Benchmark records
The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.
Cityscapes · mIoU (%) (higher is better)
5 papers, 2018–2025 · one report since 2024, not better
| Year | Best so far | Set by |
|---|---|---|
| 2018 | 75.89 | Low-Latency Video Semantic Segmentation (CVPR 2018 · 172 citations) |
| 2023 | 81.6 | Mask Propagation for Efficient Video Semantic Segmentation (NeurIPS 2023 · 5 citations) |
What has been tried
53 papers here report 614 measured changes (a component added, removed or swapped, compared with a baseline): helped 74%, no clear effect 6%, hurt 19%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add the Siam-Encoder Module | AVSS · MJ | 31.9 -> 33.3 | Helped | Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation (CVPR 2024 · 14 citations) |
| add VM800 training data | Real-world benchmark [30] · MAD# | 3.16 -> 2.55 | Helped | MatAnyone: Stable Video Matting with Consistent Memory Propagation (CVPR 2025 · 10 citations) |
| Add DenseVP | ACDC val · mIoU | 77.15 -> 77.48 | Helped | Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes (CVPR 2024 · 9 citations) |
| Add CRL | SUN-SEG-Easy · maxDice | 0.793 -> 0.810 | Helped | An Embedding-Unleashing Video Polyp Segmentation Framework via Region Linking and Scale Alignment (AAAI 2024 · 7 citations) |
| add TDF to the baseline | VIPER → Cityscapes-Seq · mIoU | 48.9 -> 51.4 | Helped | Pay Attention to Target: Relation-Aware Temporal Consistency for Domain Adaptive Video Semantic Segmentation (AAAI 2024 · 5 citations) |
| Add context prototypes to global prototypes | Cityscapes val, 1/30 labeled · mIoU | 46.78 (+3.10) -> 50.14 (+6.46) | Helped | Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation (CVPR 2024 · 5 citations) |
| add shifted representation | VSPW · mIoU | 38.9 -> 39.5 | Helped | Exploiting Temporal State Space Sharing for Video Semantic Segmentation (CVPR 2025 · 4 citations) |
| Set consistency loss weight λ to 0.2 instead of λ = 0.5 | UAVid · TC | 92.01 -> 90.72 | Hurt | High Temporal Consistency through Semantic Similarity Propagation in Semi-Supervised Video Semantic Segmentation for Autonomous Flight (CVPR 2025 · 4 citations) |
| Add a thermal infrared branch to labeled RGB training | MVSeg 1/4 · mIoU | 35.79% → 36.88% (+1.09%) | Helped | Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark (NeurIPS 2024 · 3 citations) |
| add cross-window association | SemanticKITTI validation · LSTQ | 49.2 -> 51.1 | Helped | Zero-Shot 4D Lidar Panoptic Segmentation (CVPR 2025 · 2 citations) |
| add cosine-similarity-weighted linear interpolation | VSPW validation · mVC8 | 84.3 -> 85.0 | Helped | Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · 2 citations) |
| Add masked modulation to VidSeg | VSPW first 30 val videos · mIoU | 43.4 -> 45.6 | Helped | VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models (CVPR 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 9 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- VSPW · 2 of 9 papers
- Cityscapes · 2 of 9 papers
- YouTube-VOS · 2 of 9 papers
- DAVIS-2017 · 2 of 9 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 36 papers; from OpenAlex and the papers' affiliations).
- SenseTime · 3 papers
- Tsinghua University · 2 papers
- University of Science and Technology of China · 2 papers
- Nankai University · 2 papers
- ETH Zurich · 2 papers
- Nanyang Technological University · 2 papers
Use it
Download BibTeX of 40 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Mask propagation for unsupervised video segmentation (67 papers)
- Matching-based video object segmentation (86 papers)
Elsewhere in the topic
- Self-supervised video representation learning (167 papers)
- Video restoration with temporal priors (159 papers)
- Layered video decomposition and dynamics (140 papers)
- Stochastic video prediction (125 papers)
- Physics-inspired motion prediction (113 papers)
- Sign language and physiological video analysis (99 papers)
- Weakly supervised video anomaly detection (99 papers)
- Spatio-temporal predictive modeling (91 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).