Zeroshot Video Question Answer On Tgif Qa
Metriken
Accuracy
Confidence Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy | Confidence Score |
|---|---|---|
| elysium-exploring-object-level-perception-in | 66.6 | 3.6 |
| minigpt4-video-advancing-multimodal-llms-for | 72.22 | - |
| ts-llava-constructing-visual-tokens-through | 81.0 | 4.2 |
| videochat-chat-centric-video-understanding | 34.4 | 2.3 |
| slowfast-llava-a-strong-training-free | 80.6 | 4.3 |
| video-llava-learning-united-visual-1 | 70.0 | 4.0 |
| videogpt-integrating-image-and-video-encoders | 74.6 | 4.1 |
| linvt-empower-your-image-level-large-language | 81.3 | 4.3 |
| an-image-grid-can-be-worth-a-video-zero-shot | 79.1 | 4.2 |
| video-chatgpt-towards-detailed-video | 51.4 | 3.0 |
| pllava-parameter-free-llava-extension-from-1 | 80.6 | 4.3 |
| chat-univi-unified-visual-representation | 69.0 | 3.8 |
| zero-shot-video-question-answering-via-frozen | 41.9 | - |
| tarsier-recipes-for-training-and-evaluating-1 | 82.5 | 4.4 |