Research map / Video / Video-language understanding
ActBERT: Learning Global-Local Video-Text Representations
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 ActBERT instead of VideoBert + S3D | Video captioning · YouCook2 val | METEOR: 11.94 -> 13.30 | Helped |
| Add local region cues to ActBERT (ablation) | ActBERT · COIN | Frame Accuracy (%): 52.10 -> 56.95 | Helped |
| Add local region cues to ActBERT (ablation) | ActBERT · CrossTask | Average: 37.1 -> 41.4 | Helped |
| Use ActBERT instead of TVJE +FT | Text-video retrieval · YouCook2 | R@1: 8.2 -> 9.6 | Helped |
| Fine-tune ActBERT on the MSR-VTT training set | ActBERT · MSR-VTT | R@1: 8.6 -> 16.3 | Helped |
| Use ActBERT instead of JSFusion | Video question answering · MSR-VTT | Accuracy: 83.4 -> 85.7 | Helped |
| Use ActBERT instead of JSFusion | Video question answering · LSMDC | Accuracy: 45.5 -> 48.6 | Helped |
Closest papers by meaning
- SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling (CVPR 2024 · similarity 0.86)
- OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition (CVPR 2024 · similarity 0.86)
- Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding (ICLR 2024 · similarity 0.86)
- Kronecker Mask and Interpretive Prompts are Language-Action Video Learners (ICLR 2025 · similarity 0.86)
- Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models (CVPR 2025 · similarity 0.85)
- OmniViD: A Generative Framework for Universal Video Understanding (CVPR 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.