Research map / Video / Action recognition
SST: Single-Stream Temporal Action Proposals
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 |
|---|---|---|---|
| Use single-pass SST proposals instead of DAPs proposals | Temporal action proposal generation · THUMOS’14 test, 1000 proposals | Recall@tIoU=0.8: 0.573 -> 0.672 | Helped |
| Use single-pass SST proposals instead of S-CNN-prop proposals | Temporal action proposal generation · THUMOS’14 test, 1000 proposals | Recall@tIoU=0.8: 0.524 -> 0.672 | Helped |
| Use single-pass SST rather than DAPs | Temporal action proposal generation · THUMOS’14 test | FPS: 134 -> 308 | Helped |
| Use single-pass SST rather than S-CNN-prop | Temporal action proposal generation · THUMOS’14 test | FPS: 60 -> 308 | Helped |
| Use SST proposals instead of DAPs proposals | Temporal action proposal generation · THUMOS’14 test, 1000 proposals | Recall@tIoU=0.6: 0.916 -> 0.920 | Mixed |
| Use SST proposals instead of DAPs proposals | Temporal action proposal generation · ActivityNet validation, @600 proposals | Average recall: 0.257 -> 0.288 | Helped |
| Use SST proposals instead of DAPs proposals | Temporal action proposal generation · ActivityNet ≤1024, @600 proposals | Average recall: 0.433 -> 0.494 | Helped |
| Use SST proposals with the S-CNN classifier instead of the S-CNN full system | Temporal action detection · THUMOS’14 test | mAP: 0.19 -> 0.23 | Helped |
| Use SST proposals rather than DAPs proposals with the VLAD-based SVM classifier | Temporal action detection · THUMOS’14 test, 200 proposals | mAP: 13.9 -> 13.94 | No clear effect |
Closest papers by meaning
- Temporal Convolutional Networks for Action Segmentation and Detection (CVPR 2017 · similarity 0.88)
- Adapting Short-Term Transformers for Action Detection in Untrimmed Videos (CVPR 2024 · similarity 0.88)
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos (CVPR 2017 · similarity 0.87)
- SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation (CVPR 2020 · similarity 0.87)
- Rethinking the Faster R-CNN Architecture for Temporal Action Localization (CVPR 2018 · similarity 0.87)
- End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames (CVPR 2024 · similarity 0.85)
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.