Research map / Video / Action recognition
Weakly-Supervised Action Segmentation With Iterative Soft Boundary Assignment
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 |
|---|---|---|---|
| Add soft boundary assignment (ablation) | TCFPN + ISBA · Breakfast weakly-supervised action segmentation | accuracy: 37.8 -> 38.4 | Helped |
| Add soft boundary assignment (ablation) | TCFPN + ISBA · Breakfast weakly-supervised action segmentation | IoD: 41.8 -> 40.6 | Hurt |
| Add soft boundary assignment (ablation) | TCFPN + ISBA · Breakfast weakly-supervised action alignment | accuracy: 55.7 -> 56.7 | Helped |
| Add soft boundary assignment (ablation) | TCFPN + ISBA · Breakfast weakly-supervised action alignment | Acc.-b.g.: 55.8 -> 55.9 | Helped |
| Add soft boundary assignment (ablation) | TCFPN + ISBA · Breakfast weakly-supervised action alignment | IoU: 38.1 -> 38.7 | Helped |
| Add soft boundary assignment (ablation) | TCFPN + ISBA · Breakfast weakly-supervised action alignment | IoD: 53.0 -> 54.0 | Helped |
| Use TCFPN instead of ED-TCN with ISBA | ISBA · Breakfast weakly-supervised action segmentation | accuracy: 32.0 -> 38.4 | Helped |
| Use TCFPN instead of ED-TCN with ISBA | ISBA · Hollywood Extended weakly-supervised action segmentation | IoD: 10.7 -> 18.3 | Helped |
| Use TCFPN instead of ED-TCN with ISBA | ISBA · Hollywood Extended weakly-supervised action alignment | IoU: 26.2 -> 22.3 | Hurt |
| Use video-level recognition loss to select the stopping iteration instead of the prior stop criterion | ISBA · Breakfast first split | accuracy: 38.7 -> 39.8 | Helped |
Closest papers by meaning
- Weakly Supervised Action Learning With RNN Based Fine-To-Coarse Modeling (CVPR 2017 · similarity 0.91)
- MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation (CVPR 2019 · similarity 0.90)
- SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation (CVPR 2020 · similarity 0.90)
- Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints (CVPR 2018 · similarity 0.90)
- Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment (CVPR 2024 · similarity 0.88)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.87)
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.