Research map / Video / Video segmentation and tracking
General and Task-Oriented Video Segmentation
Mu Chen, Liulei Li, Wenguan Wang, Ruijie Quan, Yi Yang
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 shape-position aware query matching (ablation) | GvSeg baseline · VIPSeg val | VPQ: 36.0 -> 37.8 | Improved |
| add task-oriented query initialization and association (ablation) | GvSeg · VIPSeg val | VPQ: 37.8 -> 40.1 | Improved |
| add task-oriented temporal contrastive learning sampling (ablation) | GvSeg · VIPSeg val | VPQ: 40.1 -> 41.2 | Improved |
| combine all task-oriented components (ablation) | GvSeg · VIPSeg val | VPQ: 36.0 -> 44.0 | Improved |
| add shape and position cues to thing object association (ablation) | GvSeg · VIPSeg val | VPQ: 42.1 -> 44.0 | Improved |
| add shape and position cues to stuff object association (ablation) | GvSeg · VIPSeg val | VPQ: 42.1 -> 41.7 | Hurt |
| sample thing examples from whole video and stuff examples from dataset queue instead of nearby frames (ablation) | GvSeg temporal contrastive learning · VIPSeg val | VPQ: 40.1 -> 44.0 | Improved |
| increase queue length from 100 to 200 (ablation) | GvSeg · VIPSeg val | VPQ: 44.0 -> 44.1 | No clear effect |
| increase histogram bins beyond 36x12 (ablation) | shape-position descriptor · VIPSeg val | VPQ: 44.0 -> 43.9 (36x18), 44.0 (48x12) | No clear effect |
| apply task-oriented design in general video segmentation on Occluded-VIS | GvSeg · Occluded-VIS val R-50 | AP: 31.1 -> 35.9 vs TarVIS | 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.
- Tube-Link — Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation (ICCV 2023) · better on 3 of 3 shared results
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
- A Survey on Deep Learning Technique for Video Segmentation (TPAMI 2022 · similarity 0.88)
- Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation (CVPR 2022 · similarity 0.88)
- LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation (TPAMI 2025 · similarity 0.87)
- GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation (CVPR 2025 · similarity 0.87)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 2025 · similarity 0.86)
- SyncVIS: Synchronized Video Instance Segmentation (NeurIPS 2024 · 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.
