Research map / Video / Action recognition
Temporal Action Localization in Untrimmed Videos via Multi-Stage CNNs
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 the full Segment-CNN framework instead of DTF | Temporal action localization · MEXaction2 | mAP: 1.7 -> 7.4 | Helped |
| Use the full Segment-CNN framework instead of Oneata et al. | Temporal action localization · THUMOS 2014, IoU 0.5 | mAP: 15.0 -> 19.0 | Helped |
| Add the proposal network to filter background segments (ablation) | S-CNN · THUMOS 2014, IoU 0.5 | mAP: 17.1 -> 19.0 | Helped |
| Initialize the localization network from the classification network (ablation) | S-CNN · THUMOS 2014 | mAP | Helped |
| Add the localization network with overlap-aware loss (ablation) | S-CNN · THUMOS 2014 | mAP | Helped |
| Vary alpha in the overlap loss from 0.25 to 1.0 (ablation) | S-CNN localization network · THUMOS 2014 | mAP | No clear effect |
Closest papers by meaning
- Temporal Action Localization by Structured Maximal Sums (CVPR 2017 · similarity 0.93)
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos (CVPR 2017 · similarity 0.93)
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network (CVPR 2018 · similarity 0.92)
- Exploring Temporal Preservation Networks for Precise Temporal Action Localization (AAAI 2018 · similarity 0.92)
- Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization (CVPR 2019 · similarity 0.91)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.89)
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.