Research map / Video / Action recognition
Learning Action Changes by Measuring Verb-Adverb Textual Relationships
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 verb-adverb textual relationships as regression targets instead of fixed δ (ablation) | REG · HowTo100M Adverbs | mAP W: 0.320 -> 0.555 | Helped |
| Use verb-adverb textual relationships as regression targets instead of fixed δ (ablation) | REG · Adverbs in Recipes | mAP W: 0.554 -> 0.613 | Helped |
| Use verb-adverb textual relationships as regression targets instead of fixed δ (ablation) | REG · ActivityNet Adverbs | mAP W: 0.115 -> 0.119 | No clear effect |
| Use verb-adverb textual relationships as regression targets instead of fixed δ (ablation) | REG · MSR-VTT Adverbs | mAP W: 0.203 -> 0.282 | Helped |
| Use verb-adverb textual relationships as regression targets instead of fixed δ (ablation) | REG · VATEX Adverbs | mAP W: 0.175 -> 0.261 | Helped |
| Use regression rather than classification (ablation) | Adverbs in Recipes · Adverbs in Recipes | mAP W: 0.606 -> 0.613 | Helped |
| Use regression rather than classification (ablation) | HowTo100M Adverbs · HowTo100M Adverbs | mAP M: 0.420 -> 0.423 | No clear effect |
| Remove action labels at test time | REG · Adverbs in Recipes | mAP W: 0.613 -> 0.520 | Hurt |
| Train without antonym pairings (ablation) | REG · Adverbs in Recipes | mAP W: 0.613 -> 0.667 | Helped |
| Train without antonym pairings (ablation) | REG · HowTo100M Adverbs | mAP M: 0.423 -> 0.481 | Helped |
| Add an MLP to Action Modifiers (ablation) | Action Modifiers · HowTo100M Adverbs | mAP W: 0.406 -> 0.279 | Hurt |
| Add an MLP to Action Modifiers (ablation) | Action Modifiers · Adverbs in Recipes | Acc-A: 0.857 -> 0.860 | No clear effect |
Closest papers by meaning
- Action Modifiers: Learning From Adverbs in Instructional Videos (CVPR 2020 · similarity 0.94)
- Kronecker Mask and Interpretive Prompts are Language-Action Video Learners (ICLR 2025 · similarity 0.84)
- Open-Vocabulary Video Relation Extraction (AAAI 2024 · similarity 0.84)
- SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization (AAAI 2025 · similarity 0.84)
- Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection? (NeurIPS 2024 · similarity 0.83)
- Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition (NeurIPS 2025 · similarity 0.83)
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.