Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
One-Shot Learning of Scene Locations via Feature Trajectory Transfer
Check 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 |
|---|---|---|---|
| Add feature trajectory transfer samples (ablation) | One-shot SVC with Places-CNN fc7 features · TADB scene locations | accuracy: 78.0 ± 4.5 -> 80.7 ± 4.5 | Helped |
| Add random-trajectory synthetic samples (ablation) | One-shot SVC with Places-CNN fc7 features · TADB scene locations | accuracy: 78.0 ± 4.5 -> 77.7 ± 4.5 | Hurt |
| Add feature trajectory transfer samples (ablation) | One-shot SVC with SUN attribute features · TADB scene locations | accuracy: 61.2 ± 4.9 -> 61.7 ± 5.0 | No clear effect |
| Add random-trajectory synthetic samples (ablation) | One-shot SVC with SUN attribute features · TADB scene locations | accuracy: 61.2 ± 4.9 -> 60.5 ± 5.1 | Hurt |
| Add metric learning [7] | One-shot SVC with Places-CNN fc7 features · TADB scene locations | accuracy: 78.0 ± 4.5 -> 88.2 ± 3.9 | Helped |
| Add trajectory-transfer samples to metric learning [7] (ablation) | One-shot SVC with Places-CNN fc7 features · TADB scene locations | accuracy: 88.2 ± 3.9 -> 89.2 ± 3.9 | Helped |
| Add metric learning [24] | One-shot SVC with Places-CNN fc7 features · TADB scene locations | accuracy: 78.0 ± 4.5 -> 80.6 ± 4.6 | Helped |
| Add trajectory-transfer samples to metric learning [24] (ablation) | One-shot SVC with Places-CNN fc7 features · TADB scene locations | accuracy: 80.6 ± 4.6 -> 84.1 ± 4.1 | Helped |
| Add metric learning [7] | One-shot SVC with SUN attribute features · TADB scene locations | accuracy: 61.2 ± 4.9 -> 61.6 ± 5.2 | No clear effect |
| Add trajectory-transfer samples to metric learning [7] (ablation) | One-shot SVC with SUN attribute features · TADB scene locations | accuracy: 61.6 ± 5.2 -> 61.2 ± 5.2 | Hurt |
| Add metric learning [24] | One-shot SVC with SUN attribute features · TADB scene locations | accuracy: 61.2 ± 4.9 -> 61.8 ± 4.5 | No clear effect |
| Add trajectory-transfer samples to metric learning [24] (ablation) | One-shot SVC with SUN attribute features · TADB scene locations | accuracy: 61.8 ± 4.5 -> 63.5 ± 4.4 | Helped |
Closest papers by meaning
- Temporal Residual Networks for Dynamic Scene Recognition (CVPR 2017 · similarity 0.84)
- Trajectory Convolution for Action Recognition (NeurIPS 2018 · similarity 0.83)
- GTR: A General, Multi-View, and Dynamic Framework for Trajectory Representation Learning (ICML 2025 · similarity 0.82)
- Moving Off-the-Grid: Scene-Grounded Video Representations (NeurIPS 2024 · similarity 0.82)
- FM-ChangeNet: Learning Change through Pathwise Feature Transport (NeurIPS 2026 · similarity 0.82)
- FeatWalk: Enhancing Few-Shot Classification through Local View Leveraging (AAAI 2024 · similarity 0.82)
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.