Research map / Video / Video-language understanding
Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning
Seung Hyup Baek, Jimin Lee, Hyeongkeun Lee, Jae Won Cho
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 role specific query initialization (ablation) | PDVC · YouCook2 (ablation, PDVC baseline) | CIDEr: 29.69 -> 32.33 | Improved |
| add overlap suppression loss (ablation) | PDVC · YouCook2 (ablation, PDVC baseline) | F1: 26.81 -> 31.22 | Improved |
| add overlap suppression loss (ablation) | PDVC · YouCook2 (ablation, PDVC baseline) | METEOR: 5.56 -> 5.41 | Hurt |
| add concept guider (ablation) | PDVC · YouCook2 (ablation, PDVC baseline) | CIDEr: 29.69 -> 31.40 | Improved |
| add cross-task contrastive alignment to role specific queries (ablation) | RSQI · YouCook2 (ablation, PDVC baseline) | CIDEr: 32.33 -> 34.48 | Improved |
| add concept guider (ablation) | RSQI+CTCA+OSL · YouCook2 (ablation, PDVC baseline) | CIDEr: 36.63 -> 39.18 | Improved |
| add overlap suppression loss (ablation) | RSQI+CTCA+CG · YouCook2 (ablation, PDVC baseline) | CIDEr: 36.93 -> 39.18 | Improved |
| add CTCA (ablation) | RSQI+OSL+CG · YouCook2 (ablation, PDVC baseline) | CIDEr: 34.92 -> 39.18 | Improved |
| add GT-aware weight alpha to OSL (ablation) | ROS-DVC · YouCook2 (ablation, PDVC baseline) | CIDEr: 34.81 -> 39.18 | Improved |
| add GT-aware weight alpha to OSL (ablation) | ROS-DVC · YouCook2 (ablation, PDVC baseline) | Recall: 31.01 -> 29.34 | Hurt |
| set OSL gamma to 0.25 instead of 0.45 (ablation) | ROS-DVC · YouCook2 (ablation, PDVC baseline) | CIDEr: 35.76 -> 39.18 | Improved |
| use 50 queries per set instead of 10 (ablation) | ROS-DVC · YouCook2 (ablation, PDVC baseline) | CIDEr: 28.72 -> 39.18 | Improved |
Closest papers by meaning
- VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning (AAAI 2025 · similarity 0.89)
- Localizing Events in Videos with Multimodal Queries (CVPR 2025 · similarity 0.89)
- Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning (AAAI 2025 · similarity 0.88)
- Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval (CVPR 2024 · similarity 0.88)
- HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning (AAAI 2025 · similarity 0.87)
- Dense Video Object Captioning from Disjoint Supervision (ICLR 2025 · similarity 0.87)
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.
