Research map / Video / Action recognition
SAP: Self-Adaptive Proposal Model for Temporal Action Detection Based on Reinforcement Learning
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 |
|---|---|---|---|
| Use SAP's adaptive proposal generation and regression | THUMOS'14 temporal action detection · THUMOS'14 | mAP at 50% IoU: 8.4% | Helped |
| Remove temporal pooling while retaining regression (ablation) | SAP · THUMOS'14 | mAP at 50% IoU | Hurt |
| Add temporal pooling (ablation) | SAP · THUMOS'14 | proposal recall at IoU=0.5 | Mixed |
| Remove regression (ablation) | SAP without temporal pooling · THUMOS'14 | mAP at 50% IoU | Hurt |
| Add localization regression (ablation) | SAP without temporal pooling · THUMOS'14 | mAP at 50% IoU | Helped |
Closest papers by meaning
- End-To-End Learning of Action Detection From Frame Glimpses in Videos (CVPR 2016 · similarity 0.89)
- Tree-Structured Policy Based Progressive Reinforcement Learning for Temporally Language Grounding in Video (AAAI 2020 · similarity 0.86)
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations (NeurIPS 2025 · similarity 0.86)
- SST: Single-Stream Temporal Action Proposals (CVPR 2017 · similarity 0.86)
- Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model (CVPR 2019 · similarity 0.85)
- LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching (NeurIPS 2026 · similarity 0.85)
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.