Research map / Video / Video segmentation and tracking
STDDNet: Harnessing Mamba for Video Polyp Segmentation via Spatial-aligned Temporal Modeling and Discriminative Dynamic Representation Learning
Guilian Chen, Huisi Wu, Jing Qin
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 STDP module (ablation) | PVTv2-B2 baseline · SUN-SEG-Easy | Dice (%): 82.73 -> 84.73 | Improved |
| add STDP module (ablation) | PVTv2-B2 baseline · SUN-SEG-Hard | Dice (%): 80.29 -> 83.48 | Improved |
| add DDFE module (ablation) | PVTv2-B2 baseline · SUN-SEG-Easy | Dice (%): 82.73 -> 84.54 | Improved |
| add DDFE module (ablation) | PVTv2-B2 baseline · SUN-SEG-Hard | Dice (%): 80.29 -> 83.79 | Improved |
| add DDFE on top of STDP (ablation) | STDDNet · SUN-SEG-Easy | Dice (%): 84.73 -> 85.86 | Improved |
| add random masking in STDP (ablation) | STDDNet · SUN-SEG-Hard | Dice (%): 83.06 -> 83.48 | Improved |
| add filter in STDP (ablation) | STDDNet · SUN-SEG-Hard | Dice (%): 83.23 -> 83.48 | Improved |
| add mask guidance in STDP (ablation) | STDDNet · SUN-SEG-Hard | Dice (%): 82.95 -> 83.48 | Improved |
| add position compensation in DDFE (ablation) | STDDNet · SUN-SEG-Hard | Dice (%): 82.16 -> 83.79 | Improved |
| add reverse operation in DDFE (ablation) | STDDNet · SUN-SEG-Hard | Dice (%): 83.15 -> 83.79 | Improved |
| add activation ratio in DDFE (ablation) | STDDNet · SUN-SEG-Hard | Dice (%): 82.82 -> 83.79 | Improved |
| use PVTv2-B2 instead of Res2Net-50 backbone | STDDNet · SUN-SEG-Hard | Dice (%): 83.45 -> 84.59 | Improved |
Later papers that compared with this method
1 later accepted paper reports STDDNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis (CVPR 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- VideoMamba — VideoMamba: State Space Model for Efficient Video Understanding (ECCV 2024) · better on 5 of 5 shared results
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
- VPSentry: Semi-supervised Video Polyp Segmentation via Sentry-guided Long-term Prototype Fusion with Correlation Dynamic Propagation (AAAI 2026 · similarity 0.90)
- An Embedding-Unleashing Video Polyp Segmentation Framework via Region Linking and Scale Alignment (AAAI 2024 · similarity 0.88)
- Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation (NeurIPS 2025 · similarity 0.84)
- Polyper: Boundary Sensitive Polyp Segmentation (AAAI 2024 · similarity 0.84)
- Boost the Inference with Co-training: A Depth-guided Mutual Learning Framework for Semi-supervised Medical Polyp Segmentation (CVPR 2025 · similarity 0.84)
- S³-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation (AAAI 2025 · similarity 0.84)
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.
