Research map / Video / Video-language understanding
Object-Aware Aggregation With Bidirectional Temporal Graph for Video Captioning
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 |
|---|---|---|---|
| Add object-aware aggregation with only the backward temporal graph (ablation) | Global-frame VLAD baseline · MSVD | BLEU@4: +0.6% | Helped |
| Add object-aware aggregation with only the backward temporal graph (ablation) | Global-frame VLAD baseline · MSVD | METEOR: +1.3% | Helped |
| Add object-aware aggregation with only the backward temporal graph (ablation) | Global-frame VLAD baseline · MSVD | CIDEr: +1.7% | Helped |
| Add object-aware aggregation with only the backward temporal graph (ablation) | Global-frame VLAD baseline · MSR-VTT | BLEU@4: +1.2% | Helped |
| Add object-aware aggregation with only the backward temporal graph (ablation) | Global-frame VLAD baseline · MSR-VTT | METEOR: +1.0% | Helped |
| Add object-aware aggregation with only the backward temporal graph (ablation) | Global-frame VLAD baseline · MSR-VTT | CIDEr: +3.0% | Helped |
| Use both forward and backward temporal graphs instead of a single-direction graph (ablation) | OA with Forward/Backward TG · MSVD | BLEU@4: 3.25% | Helped |
| Use both forward and backward temporal graphs instead of a single-direction graph (ablation) | OA with Forward/Backward TG · MSVD | METEOR: 1.15% | Helped |
| Use both forward and backward temporal graphs instead of a single-direction graph (ablation) | OA with Forward/Backward TG · MSVD | CIDEr: 5.45% | Helped |
| Add object-aware aggregation with the forward temporal graph (ablation) | Global-frame VLAD baseline · MSVD | BLEU@4: 52.7 -> 54.0 | Helped |
| Add object-aware aggregation with the forward temporal graph (ablation) | Global-frame VLAD baseline · MSR-VTT | BLEU@4: 39.6 -> 40.8 | Helped |
| Use OA-BTG instead of the strongest listed baseline | Video captioning · MSVD | BLEU@4: 53.8 -> 56.9 | Helped |
Closest papers by meaning
- Spatio-Temporal Graph for Video Captioning With Knowledge Distillation (CVPR 2020 · similarity 0.91)
- Dense Video Object Captioning from Disjoint Supervision (ICLR 2025 · similarity 0.88)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.88)
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.87)
- Event-Equalized Dense Video Captioning (CVPR 2025 · similarity 0.86)
- OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning (NeurIPS 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.