Research map / Video / Video segmentation and tracking
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| apply spatial, temporal, and historical consistency learning | TRN source model · UCF-HMDB (Avg.) | accuracy: 85.2 -> 91.5 | Helped |
| apply spatial, temporal, and historical consistency learning | TRN source model · UCF-Kinetics (Avg.) | accuracy: 87.6 -> 93.0 | Helped |
| apply spatial, temporal, and historical consistency learning | TRN source model · Jester (Avg.) | accuracy: 50.3 -> 78.4 | Helped |
| apply spatial, temporal, and historical consistency learning | TRN source model · DailyDA (Avg.) | accuracy: 34.7 -> 39.2 | Helped |
| apply spatial, temporal, and historical consistency learning | TRN source model · DailyDA individual transfer tasks | accuracy | Mixed |
| add spatial consistency (ablation) | STHC · UCF→HMDB | accuracy: 87.8 -> 90.8 | Helped |
| add spatial consistency (ablation) | STHC · JS→JT | accuracy: 75.0 -> 78.4 | Helped |
| add temporal consistency (ablation) | STHC · UCF→HMDB | accuracy: 88.9 -> 90.8 | Helped |
| add temporal consistency (ablation) | STHC · JS→JT | accuracy: 70.1 -> 78.4 | Helped |
| add historical consistency (ablation) | STHC · UCF→HMDB | accuracy: 89.8 -> 90.8 | Helped |
| add historical consistency (ablation) | STHC · JS→JT | accuracy: 76.6 -> 78.4 | Helped |
| train the classifier during adaptation rather than freezing it (ablation) | STHC · UCF→HMDB | accuracy: 88.1 -> 90.8 | Helped |
Closest papers by meaning
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.90)
- Source-Free Domain Adaptation with Frozen Multimodal Foundation Model (CVPR 2024 · similarity 0.87)
- Modality-Collaborative Test-Time Adaptation for Action Recognition (CVPR 2024 · similarity 0.87)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 2025 · similarity 0.87)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.86)
- SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation (ICLR 2024 · similarity 0.86)
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.