Research map / Video / Action recognition
What If We Do Not Have Multiple Videos of the Same Action? -- Video Action Localization Using Web Images
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 web-image proposals with the full reconstruction and motion-saliency method instead of CRANE | video action localization · UCF-Sports | localization accuracy: 65.41 -> 92.72 | Helped |
| use web-image proposals with the full reconstruction and motion-saliency method instead of Negative Mining | video action localization · UCF-Sports | localization accuracy: 63.01 -> 92.72 | Helped |
| remove noisy web images using random walk (ablation) | web-image reconstruction for video action localization · UCF-Sports | localization accuracy: 65.25 -> 68.16 | Helped |
| replace whole-image features with localized image action proposals (ablation) | web-image reconstruction for video action localization · UCF-Sports | localization accuracy: 68.16 -> 83.70 | Helped |
| add sparsity and consensus constraints to proposal reconstruction (ablation) | video action proposal reconstruction · UCF-Sports | localization accuracy: 83.70 -> 88.56 | Helped |
| add motion saliency to the reconstruction-based ranking (ablation) | video action proposal ranking · UCF-Sports | localization accuracy: 88.56 -> 92.72 | Helped |
Closest papers by meaning
- Predicting the Where and What of Actors and Actions Through Online Action Localization (CVPR 2016 · similarity 0.89)
- Few-Shot Transformation of Common Actions Into Time and Space (CVPR 2021 · similarity 0.88)
- Improving Action Localization by Progressive Cross-Stream Cooperation (CVPR 2019 · similarity 0.88)
- Learning To Refactor Action and Co-Occurrence Features for Temporal Action Localization (CVPR 2022 · similarity 0.88)
- PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization (CVPR 2023 · similarity 0.87)
- 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.