Research map / Video / Action recognition
Weakly-Supervised Action Localization With Background Modeling
Phuc Xuan Nguyen, Deva Ramanan, Charless C. Fowlkes
Read the paperCheck your idea against 137,217 papers
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 background-aware loss (ablation) | foreground-only model · THUMOS14 (loss ablation) | AP@IoU=0.5: 14.7 -> 20.5 | Improved |
| add self-guided attention loss (ablation) | foreground-only model · THUMOS14 (loss ablation) | AP@IoU=0.5: 14.7 -> 19.2 | Improved |
| add self-guided attention loss (ablation) | fg + bg model · THUMOS14 (loss ablation) | AP@IoU=0.5: 20.5 -> 24.4 | Improved |
| add foreground-background clustering loss (ablation) | fg + bg model · THUMOS14 (loss ablation) | AP@IoU=0.5: 20.5 -> 23.1 | Improved |
| add clustering loss (ablation) | fg + bg + guide model · THUMOS14 (loss ablation) | AP@IoU=0.5: 24.4 -> 26.8 | Improved |
| add background-aware loss (ablation) | fg + guide + cluster model · THUMOS14 (loss ablation) | AP@IoU=0.5: 23.2 -> 26.8 | Improved |
| add self-guided loss (ablation) | fg + bg + cluster model · THUMOS14 (loss ablation) | AP@IoU=0.5: 23.1 -> 26.8 | Improved |
| replace sparsity loss with self-guided attention loss (ablation) | fg model (STPN) · THUMOS14 (loss ablation) | AP@IoU=0.5: 16.9 -> 19.2 | Improved |
| add 915 Instagram microvideos to training | full model · THUMOS14 (test) | AP@IoU=0.5: 26.8 -> 27.5 at IoU 0.5; 9.0 -> 8.6 at IoU 0.7 | Mixed |
| add 915 Instagram microvideos to training | full model · THUMOS14 (test) | AP@IoU=0.5: 60.4 -> 64.2 | Improved |
Closest papers by meaning
- Weakly-Supervised Action Localization by Hierarchically-Structured Latent Attention Modeling (ICCV 2023 · similarity 0.93)
- A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization (AAAI 2021 · similarity 0.93)
- Weakly-Supervised Action Localization by Generative Attention Modeling (CVPR 2020 · similarity 0.92)
- D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations (ICCV 2021 · similarity 0.92)
- Background-Click Supervision for Temporal Action Localization (TPAMI 2021 · 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.
