Humorous Image Captioning on OxfordTVG-HIC
86Win RateHUMORCHAIN (I)
Evaluation results
| Method | Links | |
|---|---|---|
| HUMORCHAIN (I)Strategy=Theory-Guided Multi-Stage Reasoning, Total Samples=1007, Evaluation Protocol=Pairwise comparison vs External OxfordTVG-HIC (H)2025.11 | 86 | |
| HUMORCHAIN (without discriminator) (J)Strategy=Theory-Guided Multi-Stage Reasoning (without discriminator), Total Samples=300, Evaluation Protocol=Pairwise comparison vs External OxfordTVG-HIC (H)2025.11 | 78.8 | |
| External OxfordTVG-HIC (H)Strategy=Oxford University dataset based on humor-labeled caption pairs, Total Samples=300, Evaluation Protocol=Pairwise comparison vs HUMORCHAIN (J)2025.11 | 21.2 | |
| External OxfordTVG-HIC (H)Strategy=Oxford University dataset based on humor-labeled caption pairs, Total Samples=1007, Evaluation Protocol=Pairwise comparison vs HUMORCHAIN (I)2025.11 | 14 |