Video Chaptering on VidChapters-7M Short (test)
45.5F1 ScoreChapter-Llama
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Chapter-LlamaBackbone=Llama 3.1-8B, Frame selection=Proposed, Finetuned=true2025.03 | 45.5 | 72.2 | 20.2 | 103.5 | |
| Gemini-1.5-ProBackbone=Gemini-1.5-Pro, Frame selection=Speech-based, Finetuned=false2025.03 | 41.7 | 70.6 | 11.7 | 65.3 | |
| Gemini-2.0-FlashBackbone=Gemini-2.0-Flash, Frame selection=Speech-based, Finetuned=false2025.03 | 39.9 | 69.2 | 12 | 72.8 | |
| GPT-4oBackbone=GPT-4o, Frame selection=Speech-based, Finetuned=false2025.03 | 37.7 | 68 | 8.4 | 53.8 | |
| Vid2SeqBackbone=Vid2Seq, Frame selection=Equidistant, Finetuned=true2025.03 | 33.4 | 63.7 | 15.2 | 74.9 | |
| GPT-4o-miniBackbone=GPT-4o-mini, Frame selection=Speech-based, Finetuned=false2025.03 | 32.1 | 64.5 | 7.2 | 42.4 | |
| Llama 3.1-8BBackbone=Llama 3.1-8B, Frame selection=Speech-based, Finetuned=false2025.03 | 29.9 | 63.4 | 7.1 | 34.5 | |
| Vid2SeqBackbone=Vid2Seq, Frame selection=Equidistant, Finetuned=false2025.03 | 2.5 | 28.6 | 0.3 | 0.3 |