Research map / Video / Video segmentation and tracking
Dual-Temporal Exemplar Representation Network for Video Semantic Segmentation
Xiaolong Xu, Lei Zhang, Jiayi Li, Lituan Wang, Yifan Guan, Yu Yan, Leyi Zhang, Hao Song
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 Global Temporal Exemplar Module (ablation) | DTERN · VSPW val (ablation, MiT-B1) | VEC8: 37.6 -> 37.8 | Improved |
| add Global Temporal Exemplar Module (ablation) | DTERN · VSPW val (ablation, MiT-B1) | VEC16: 38.8 -> 39.0 | Improved |
| add Global Temporal Exemplar Module (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 40.4 -> 40.3 | Hurt |
| add cluster center aggregation (SAM) instead of direct summation (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 40.0 -> 40.3 | Improved |
| use CAM instead of ResBlock (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 39.7 -> 40.3 | Improved |
| use 200 clusters instead of 32 (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 39.3 -> 40.3 | Improved |
| use 200 clusters instead of 124 (K=C) (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 39.7 -> 40.3 | Improved |
| use 200 clusters instead of 2048 (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 39.6 -> 40.3 | Improved |
| use proposed clustering instead of ClusterFormer (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 38.0 -> 40.3 | Improved |
| use proposed clustering instead of PaCaViT (ablation) | DTERN · VSPW val (ablation, MiT-B1) | mIoU: 39.7 -> 40.3 | Improved |
| use VEC instead of VC to measure temporal consistency | CFFM predictions · VSPW | Pearson correlation with ground-truth TC: 59.4 -> 88.1 | Improved |
| DTERN instead of SegFormer baseline | DTERN with MiT-B0 · VSPW val | mIoU: 33.1 -> 35.9 | Improved |
Closest papers by meaning
- Efficient Semantic Video Segmentation with Per-frame Inference (ECCV 2020 · similarity 0.88)
- Temporally Distributed Networks for Fast Video Semantic Segmentation (CVPR 2020 · similarity 0.88)
- Semantic-Assisted Object Clustering for Multi-Modal Referring Video Segmentation (TPAMI 2025 · similarity 0.88)
- Low-Latency Video Semantic Segmentation (CVPR 2018 · similarity 0.88)
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · similarity 0.88)
- Exploiting Temporal State Space Sharing for Video Semantic 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.
