Research map / Video / Action recognition
Towards Automatic Learning of Procedures From Web Instructional Videos
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 segment-level sequential prediction instead of NMS for selecting final segments | ProcNets · YouCook2 test | Jaccard: 47.6 -> 50.6 | Helped |
| Add Proposal Vector to the sequential prediction LSTM (ablation) | ProcNets-LSTM · YouCook2 test | Jaccard: 47.6 -> 50.6 | Helped |
| Add Proposal Vector to the sequential prediction LSTM (ablation) | ProcNets-LSTM · YouCook2 test | mIoU: 36.1 -> 37.0 | Helped |
| Add Location Embedding to the sequential prediction LSTM (ablation) | ProcNets-LSTM · YouCook2 test | Jaccard: 46.2 -> 50.6 | Helped |
| Add Location Embedding to the sequential prediction LSTM (ablation) | ProcNets-LSTM · YouCook2 test | mIoU: 35.1 -> 37.0 | Helped |
| Add Segment Content to the sequential prediction LSTM (ablation) | ProcNets-LSTM · YouCook2 test | Jaccard: 49.0 -> 50.6 | Helped |
| Add Segment Content to the sequential prediction LSTM (ablation) | ProcNets-LSTM · YouCook2 test | mIoU: 36.4 -> 37.0 | Helped |
| Use a bi-directional LSTM encoder rather than context-free ResNet features or LSTM-encoded features (ablation) | ProcNets · YouCook2 | evaluation metric: relative 9% | Helped |
| Reverse the order of the two video halves | ProcNets-LSTM · YouCook2 permutated test set | performance: over a half | Hurt |
Closest papers by meaning
- Data Augmentation for Instruction Following Policies via Trajectory Segmentation (AAAI 2025 · similarity 0.87)
- Procedure Knowledge Decoupled Distillation Strategy for Procedure Planning in Instructional Videos (AAAI 2025 · similarity 0.87)
- SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos (ICLR 2024 · similarity 0.86)
- Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos (CVPR 2024 · similarity 0.86)
- Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos (ICLR 2025 · similarity 0.86)
- Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis (AAAI 2024 · 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.