Research map / Video / Action recognition
Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
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 knowledge transfer from trimmed videos (ablation) | SRNet · THUMOS14 | classification accuracy (Fusion, %): 79.4 -> 87.1 | Helped |
| Add knowledge transfer from trimmed videos (ablation) | SRNet · ActivityNet1.3 | classification accuracy (Fusion, %): 86.9 -> 91.2 | Helped |
| Add the FC2 MMD loss (ablation) | TSRNet · THUMOS14 | mAP@IoU 0.1 (%): 53.5 -> 55.9 | Helped |
| Pretrain TSRNet using the 30 overlapping classes (ablation) | TSRNet · ActivityNet1.3 | Average mAP (%): 19.56 -> 21.78 | Helped |
| Transfer knowledge twice rather than once (ablation) | TSRNet · THUMOS14 | mAP | Helped |
| Set the RGB/optical-flow fusion balance parameter to large values | TSRNet temporal detection · Untrimmed video action detection | detection performance | Hurt |
Closest papers by meaning
- UntrimmedNets for Weakly Supervised Action Recognition and Detection (CVPR 2017 · similarity 0.91)
- Multi-Instance Multi-Label Action Recognition and Localization Based on Spatio-Temporal Pre-Trimming for Untrimmed Videos (AAAI 2020 · similarity 0.90)
- ActionBytes: Learning From Trimmed Videos to Localize Actions (CVPR 2020 · similarity 0.90)
- Action Recognition From Single Timestamp Supervision in Untrimmed Videos (CVPR 2019 · similarity 0.90)
- Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization (CVPR 2019 · similarity 0.89)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.88)
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.