Research map / Video / Video segmentation and tracking
MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation
Ming Dai, Sen Yang, Boqiang Duan, Wankou Yang, Jingdong Wang
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 Temporal Token Injecting (ablation) | MomentSeg-3B baseline · MeViS (valu) | J&F: 57.0 -> 58.7 | Improved |
| add Temporal Token Injecting (ablation) | MomentSeg-3B baseline · ReasonVOS | J&F: 54.1 -> 58.1 | Improved |
| add Moment-Centric Sampling on top of TTI (ablation) | MomentSeg-3B · MeViS (valu) | J&F: 58.7 -> 61.3 | Improved |
| add Moment-Centric Sampling on top of TTI (ablation) | MomentSeg-3B · Ref-DAVIS17 | J&F: 76.2 -> 76.8 | Improved |
| add BAP on top of TTI and MCS (ablation) | MomentSeg-3B · Ref-DAVIS17 | J&F: 76.8 -> 76.4 | Hurt |
| add BAP on top of TTI and MCS (ablation) | MomentSeg-3B · ReVOS (overall) | J&F: 60.4 -> 62.6 | Improved |
| use MCS instead of FirstK (ablation) | MomentSeg-3B · ReasonVOS | J&F: 55.9 -> 60.8 | Improved |
| use MCS instead of FirstK (ablation) | MomentSeg-3B · MeViS (valu) | J&F: 58.3 -> 61.3 | Improved |
| use MCS instead of Uniform sampling (ablation) | MomentSeg-3B · Ref-DAVIS17 | J&F: 76.2 -> 77.3 | Improved |
| use MCS instead of NearbyK (ablation) | MomentSeg-3B · ReasonVOS | J&F: 59.9 -> 60.8 | Improved |
| add moment-anchored updating to forward propagation (ablation) | MomentSeg-3B · MeViS (valu) | J&F: 58.9 -> 61.1 | Improved |
| add adaptive memory cleaning (ablation) | MomentSeg-3B · MeViS (valu) | J&F: 61.1 -> 61.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GLUS-7B — GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation (CVPR 2025) · better on 2 of 2 shared results
- DeRVOS — DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentation (CVPR 2026) · better on 1 of 1 shared result
- Sa2VA-8B — Sa2VA: Marrying SAM2 With MLLM for Dense Grounded Understanding of Images and Videos (TPAMI 2026) · 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
- Temporal Collection and Distribution for Referring Video Object Segmentation (ICCV 2023 · similarity 0.90)
- ReferEverything: Towards Segmenting Everything We Can Speak of in Videos (ICCV 2025 · similarity 0.89)
- DTOS: Dynamic Time Object Sensing with Large Multimodal Model (CVPR 2025 · similarity 0.89)
- Deforming Videos to Masks: Flow Matching for Referring Video Segmentation (ICLR 2026 · similarity 0.89)
- Transferable Video Moment Localization by Moment-Guided Query Prompting (AAAI 2024 · similarity 0.88)
- SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation (CVPR 2025 · similarity 0.88)
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.
