Research map / Video / Video segmentation and tracking
Towards Streaming Referring Video Segmentation via Large Language Model
Wenkang Zhang, Kaicheng Yang, Xiang An, Qiang Li, Ziyong Feng, Wankou Yang, Jiankang Deng
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 |
|---|---|---|---|
| recycle [SEG] embedding as [INFO] token across frames (SER) (ablation) | StreamingRVOS-1B · MeViS (valu) | J&F: 52.4 -> 58.5 | Improved |
| add SER to streaming Sa2VA baseline (ablation) | Sa2VA-1B-Stream · MeViS (valu) | J&F: 57.1 -> 58.5 | Improved |
| add OMCP video fine-tuning on top of SER (ablation) | StreamingRVOS-1B · MeViS (valu) | J&F: 58.5 -> 59.5 | Improved |
| add OMCP video fine-tuning on top of SER (ablation) | StreamingRVOS-1B · Ref-DAVIS | J&F: 75.0 -> 76.4 | Improved |
| add OMCP video fine-tuning on top of SER (ablation) | StreamingRVOS-4B · ReVOS (Referring) | J&F: 61.2 -> 63.0 | Improved |
| add OMCP video fine-tuning on top of SER (ablation) | StreamingRVOS-1B · RefCOCO | cIoU: 80.7 -> 80.3 | Hurt |
| add SER to Sa2VA streaming baseline (ablation) | Sa2VA-1B-Stream · Ref-DAVIS | J&F: 74.4 -> 75.0 | Mixed |
| store 2 or 3 [INFO] embeddings instead of 1 (ablation) | StreamingRVOS-1B · MeViS (valu) | J&F: 58.5 -> 58.1 (2), 58.2 (3) | No clear effect |
| store 2 [INFO] embeddings instead of 1 (ablation) | StreamingRVOS-1B · ReVOS (Referring) | J&F: 58.9 -> 60.2 | Improved |
| update [INFO] periodically or via OMCP instead of first frame only (ablation) | StreamingRVOS-1B · MeViS (valu) | J&F: 54.4 -> 59.5 | Improved |
| use OMCP adaptive update instead of updating every frame (ablation) | StreamingRVOS-1B · MeViS (valu) | J&F: 59.2 -> 59.5 | Improved |
| use OMCP adaptive update instead of updating every frame (ablation) | StreamingRVOS-1B · speed | FPS: 3.4 -> 6.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- GLUS-7B — GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation (CVPR 2025) · better on 0 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
- Deforming Videos to Masks: Flow Matching for Referring Video Segmentation (ICLR 2026 · similarity 0.90)
- ReferEverything: Towards Segmenting Everything We Can Speak of in Videos (ICCV 2025 · similarity 0.90)
- Mask Propagation for Efficient Video Semantic Segmentation (NeurIPS 2023 · similarity 0.88)
- Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation (CVPR 2022 · similarity 0.88)
- Semantic and Sequential Alignment for Referring Video Object Segmentation (CVPR 2025 · similarity 0.87)
- VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models (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.
