Research map / Video / Video segmentation and tracking
Local-Global Context Aware Transformer for Language-Guided Video Segmentation
Chen Liang, Wenguan Wang, Tianfei Zhou, Jiaxu Miao, Yawei Luo, 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 cross-modality encoder to concatenation baseline (ablation) | Baseline · A2D-S test | mIoU: 47.3 -> 54.6 | Improved |
| add local-global memory (ablation) | Locater with E_vw · A2D-S test | mIoU: 54.6 -> 57.5 | Improved |
| add deeply-supervised learning on top of E_vw and memory (ablation) | Locater · A2D-S test | mIoU: 57.5 -> 59.7 | Improved |
| add memory on top of E_vw and DSL (ablation) | Locater · A2D-S+ (avg) | mIoU: 34.8 -> 36.4 | Improved |
| use Transformer visual encoder instead of I3D (ablation) | Locater · A2D-S test | mIoU: 58.3 -> 59.7 | Improved |
| add a decoder with product distance rather than encoder-only head (ablation) | Locater · A2D-S test | mIoU: 56.8 -> 59.7 | Improved |
| use product distance instead of cosine distance (ablation) | Locater · A2D-S test | mIoU: 59.2 -> 59.7 | Improved |
| use visual-guided query instead of text-invented query (ablation) | Locater · A2D-S test | mIoU: 58.7 -> 59.7 | Improved |
| stack cross-modality encoder modules K from 1 to 3 (ablation) | Locater · A2D-S test | mIoU: 58.4 -> 59.7 | Improved |
| increase cross-modality encoder modules K from 3 to 5 (ablation) | Locater · A2D-S test | mIoU: 59.7 -> 59.7 | No clear effect |
| sample frames with intervals of 3 to 10 for global memory instead of 30 (ablation) | Locater · A2D-S test | mIoU: 59.0 -> 59.7 | No clear effect |
| add local and global memory capacity (N_l=0,N_g=0 to 2N_v,1.5N_v) (ablation) | Locater · A2D-S+ (avg) | mIoU: 34.8 -> 36.4 | Improved |
Closest papers by meaning
- Language As Queries for Referring Video Object Segmentation (CVPR 2022 · similarity 0.90)
- Deforming Videos to Masks: Flow Matching for Referring Video Segmentation (ICLR 2026 · similarity 0.90)
- OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning (NeurIPS 2024 · similarity 0.88)
- GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation (CVPR 2025 · similarity 0.87)
- Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation (AAAI 2024 · similarity 0.87)
- Semantic and Sequential Alignment for Referring Video Object Segmentation (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.
