Research map / Video / Action recognition
One-Shot Action Localization by Learning Sequence Matching Network
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 |
|---|---|---|---|
| use the learned similarity network instead of a binary SVM classifier (ablation) | One-shot localization network · THUMOS14 test-14 | mAP: 6.0 -> 13.6 | Helped |
| use a segment-based temporal representation and ranking LSTM rather than no alignment (ablation) | One-shot localization network · THUMOS14 test-14 | mAP: 7.8 -> 13.6 | Helped |
| add ranking loss to the segment-based video representation (ablation) | One-shot localization network · THUMOS14 test-14 | mAP: 12.9 -> 13.6 | Helped |
| add ranking loss to the segment-based video representation (ablation) | One-shot action recognition · One-shot action recognition | accuracy: 57.5 -> 57.4 | No clear effect |
| increase reference examples per class from 1 to 5 | Ours · THUMOS14 test-14 | mAP@IoU 0.5: 13.6 -> 14.0 | Helped |
| increase reference examples per class from 5 to 15 | Ours · THUMOS14 test-14 | mAP@IoU 0.5: 14.0 -> 14.7 | Helped |
| increase reference examples per class from 1 to 5 | Ours · ActivityNet val-20 | mAP@0.5: 22.3 -> 23.1 | Helped |
| increase reference examples per class from 1 to 5 | Ours · ActivityNet val-20 | Average mAP: 9.8 -> 10.0 | Helped |
Closest papers by meaning
- Fine-Grained Temporal Contrastive Learning for Weakly-Supervised Temporal Action Localization (CVPR 2022 · similarity 0.91)
- Learning To Refactor Action and Co-Occurrence Features for Temporal Action Localization (CVPR 2022 · similarity 0.91)
- Temporal Action Localization by Structured Maximal Sums (CVPR 2017 · similarity 0.91)
- ActionBytes: Learning From Trimmed Videos to Localize Actions (CVPR 2020 · similarity 0.91)
- Test-Time Zero-Shot Temporal Action Localization (CVPR 2024 · similarity 0.90)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.90)
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.