Video Based Generative Performance 2
평가 지표
gpt-score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | gpt-score |
|---|---|
| llama-adapter-v2-parameter-efficient-visual | 2.15 |
| moviechat-from-dense-token-to-sparse-memory | 2.42 |
| video-chatgpt-towards-detailed-video | 2.37 |
| chat-univi-unified-visual-representation | 2.81 |
| one-for-all-video-conversation-is-feasible | 2.46 |
| ts-llava-constructing-visual-tokens-through | 3.69 |
| pllava-parameter-free-llava-extension-from-1 | 3.25 |
| minigpt4-video-advancing-multimodal-llms-for | 2.67 |
| one-for-all-video-conversation-is-feasible | 2.2 |
| mvbench-a-comprehensive-multi-modal-video | 2.81 |
| slowfast-llava-a-strong-training-free | 3.57 |
| vtimellm-empower-llm-to-grasp-video-moments | 2.47 |
| videogpt-integrating-image-and-video-encoders | 3.39 |
| ppllava-varied-video-sequence-understanding | 3.81 |
| st-llm-large-language-models-are-effective-1 | 2.81 |
| video-llama-an-instruction-tuned-audio-visual | 1.79 |
| mvbench-a-comprehensive-multi-modal-video | 2.62 |
| videochat-chat-centric-video-understanding | 2.24 |