Research map / Video / Video segmentation and tracking
Fast Video Object Segmentation using the Global Context Module
Yu Li, Zhuoran Shen, Ying Shan
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 |
|---|---|---|---|
| enlarge the global context feature from 512x128 to 512x512 (ablation) | GC · DAVIS 2016 test | J&F: 86.6 -> 86.1 | No clear effect |
| enlarge the global context feature from 512x128 to 512x512 (ablation) | GC · DAVIS 2016 test | time (s): 0.040 -> 0.046 | Hurt |
| replace space-time memory with fixed-size global context | STM · Memory read, t=100 | FLOPS: 21.2 G -> 0.04 G | Improved |
| replace space-time memory with fixed-size global context | STM · Memory read, t=100 | memory: 394 MB -> 1 MB | Improved |
| replace space-time memory with global context | STM* · DAVIS 2016 val | time per frame: 0.15 -> 0.04 | Improved |
| replace space-time memory with global context | STM* · DAVIS 2016 val | J&F mean: 86.5 -> 86.6 | No clear effect |
| replace space-time memory with global context | STM* · DAVIS 2017 val | J&F mean: 71.6 -> 71.4 | No clear effect |
| replace space-time memory with global context | STM · YouTube-VOS val | overall: 79.4 -> 73.2 | Hurt |
| use equal test protocol (stride 5, no soft aggregation) for STM and GC | STM vs GC · YouTube-VOS val | J&F mean: 73.7 -> 73.2 | No clear effect |
| add soft aggregation and test input stride 1 to STM | STM · YouTube-VOS val | J&F mean: 73.7 -> 79.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FEELVOS — FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation (CVPR 2019) · better on 2 of 2 shared results
- RANet — RANet: Ranking Attention Network for Fast Video Object Segmentation (ICCV 2019) · 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
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.89)
- Video Object Segmentation With Dynamic Memory Networks and Adaptive Object Alignment (ICCV 2021 · similarity 0.89)
- XMem++: Production-level Video Segmentation From Few Annotated Frames (ICCV 2023 · similarity 0.88)
- Global Spectral Filter Memory Network for Video Object Segmentation (ECCV 2022 · similarity 0.88)
- Space-Time Memory Networks for Video Object Segmentation With User Guidance (TPAMI 2020 · similarity 0.88)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
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.
