Research map / Video / Video segmentation and tracking
Tracking and Segmenting Anything in Any Modality
Tianlu Zhang, Qiang Zhang, Guiguang Ding, Jungong Han
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add CpMoE sub-module of DeMoE (ablation) | SATA · LasHeR | PR: 75.8 -> 77.8 | Improved |
| add SaMoE sub-module of DeMoE (ablation) | SATA · LasHeR | PR: 75.3 -> 77.8 | Improved |
| add MoE loss (ablation) | SATA · BDD MOTS | MOTSA: 36.9 -> 38.1 | Improved |
| add candidates generation module (CGM) (ablation) | SATA · GOT10K | AO: 78.5 -> 81.3 | Improved |
| add fine-grained memory (ablation) | SATA · BDD MOTS | MOTSA: 34.1 -> 38.1 | Improved |
| add spatiotemporal memory (ablation) | SATA · BDD MOTS | MOTSA: 30.7 -> 38.1 | Improved |
| add memory-enhanced module (MEM) (ablation) | SATA · BDD MOTS | MOTSA: 29.1 -> 38.1 | Improved |
| add MEM (ablation) | SATA · UniRTL | HOTA: 54.2 -> 59.7 | Improved |
| use DeMoE instead of UnTrack shared embedding (ablation) | SATA · LasHeR | PR: 74.2 -> 77.8 | Improved |
| use DeMoE instead of XTrack MeMoE (ablation) | SATA · DepthTrack | PR: 65.2 -> 67.9 | Improved |
| use DeMoE instead of FlexTrack HMOE-Fuse (ablation) | SATA · VisEvent | PR: 78.7 -> 82.8 | Improved |
| use DeMoE instead of SUTrack unified representation (ablation) | SATA · LasHeR | PR: 75.3 -> 77.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CSTrack — CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features (ICML 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Tracking Anything with Decoupled Video Segmentation (ICCV 2023 · similarity 0.89)
- A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship (NeurIPS 2023 · similarity 0.89)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.88)
- Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation (AAAI 2024 · similarity 0.88)
- Matching Anything by Segmenting Anything (CVPR 2024 · similarity 0.87)
- A Distractor-Aware Memory for Visual Object Tracking with SAM2 (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
