| visual-question-answering-vqa-on-core-mm | LLaMA-Adapter V2 | #6 | Overall score: 30.46Deductive: 28.7Abductive: 46.12… |
| video-based-generative-performance-benchmarking-temporal-understanding-on-videoinstruct | LLaMA Adapter | #15 | gpt-score: 1.98 |
| video-based-generative-performance-benchmarking-consistency-on-videoinstruct | LLaMA Adapter | #17 | gpt-score: 2.15 |
| video-based-generative-performance-benchmarking-contextual-understanding-on-videoinstruct | LLaMA Adapter | #17 | gpt-score: 2.30 |
| video-based-generative-performance-benchmarking-correctness-of-information-on-videoinstruct | LLaMA Adapter | #17 | gpt-score: 2.03 |
| video-based-generative-performance-benchmarking-detail-orientation-on-videoinstruct | LLaMA Adapter | #17 | gpt-score: 2.32 |
| video-based-generative-performance-benchmarking-on-videoinstruct | LLaMA Adapter | #22 | mean: 2.16Correctness of Information: 2.03Detail Orientation: 2.32… |
| video-question-answering-on-activitynet-qa | LLaMA Adapter V2 | #26 | Accuracy: 34.2Confidence score: 2.7 |
| zeroshot-video-question-answer-on-activitynet-qa | LLaMA Adapter | #26 | Accuracy: 34.2Confidence Score: 2.7 |
| zeroshot-video-question-answer-on-msvd-qa | LLaMA Adapter-7B | #27 | Accuracy: 54.9Confidence Score: 3.1 |
| zeroshot-video-question-answer-on-msrvtt-qa | LLaMA Adapter-7B | #29 | Accuracy: 43.8Confidence Score: 2.7 |
| visual-question-answering-on-mm-vet | LLaMA-Adapter v2-7B | #172 | GPT-4 score: 31.4±0.1Params: 7B |