Research map / Video / Action recognition
Weakly-Supervised Action Localization by Hierarchically-Structured Latent Attention Modeling
Guiqin Wang, Peng Zhao, Cong Zhao, Shusen Yang, Jie Cheng, Luziwei Leng, Jianxing Liao, Qinghai Guo
AI-extracted. The measured effects below were read by AI from the paper's full text (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 change-point detection module (L_ELBO) on top of full EFC (ablation) | AHLM · THUMOS14 | avg mAP: 44.6 -> 47.0 | Improved |
| add change-point module to foreground-only model (ablation) | foreground loss model · THUMOS14 | avg mAP: 26.2 -> 28.3 | Improved |
| add change-point module to foreground+background model (ablation) | L_fg + L_bg · THUMOS14 | avg mAP: 32.0 -> 34.5 | Improved |
| add background and context losses to foreground loss (ablation) | AHLM EFC · THUMOS14 | avg mAP: 26.2 -> 44.6 | Improved |
| add change-point detection points to a MIL-based method (ablation) | MIL-based method · THUMOS14 | avg mAP: 24.8 -> 28.5 | Improved |
| add change-point module (ablation) | foreground-only model · THUMOS14 (IoU 0.7) | mAP@0.7: 5.3 -> 5.4 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ASM-Loc — ASM-Loc: Action-Aware Segment Modeling for Weakly-Supervised Temporal Action Localization (CVPR 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Weakly-Supervised Action Localization With Background Modeling (ICCV 2019 · similarity 0.93)
- Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning (ECCV 2020 · similarity 0.93)
- A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization (AAAI 2021 · similarity 0.93)
- Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization (CVPR 2023 · similarity 0.92)
- Temporal Action Localization in the Deep Learning Era: A Survey (TPAMI 2023 · similarity 0.92)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.92)
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.
