| vcgbench-diverse-on-videoinstruct | BT-Adapter | #4 | mean: 2.19Correctness of Information: 2.20Detail Orientation: 2.62… |
| zero-shot-action-recognition-on-kinetics-400-zero-shot-action-classification | BT-Adapter | #4 | Accuracy: 64.3 |
| zero-shot-video-retrieval-on-lsmdc | BT-Adapter | #6 | text-to-video R@1: 19.5text-to-video R@5: 35.9… |
| zero-shot-video-retrieval-on-activitynet | BT-Adapter | #8 | text-to-video R@1: 37.0text-to-video R@5: 66.7… |
| video-question-answering-on-activitynet-qa | BT-Adapter (zero-shot) | #10 | Accuracy: 46.1Confidence score: 3.6 |
| video-based-generative-performance-benchmarking-consistency-on-videoinstruct | BT-Adapter | #12 | gpt-score: 2.46 |
| video-based-generative-performance-benchmarking-consistency-on-videoinstruct | BT-Adapter (zero-shot) | #16 | gpt-score: 2.2 |
| video-based-generative-performance-benchmarking-contextual-understanding-on-videoinstruct | BT-Adapter | #12 | gpt-score: 3.27 |
| video-based-generative-performance-benchmarking-contextual-understanding-on-videoinstruct | BT-Adapter (zero-shot) | #14 | gpt-score: 2.89 |
| video-based-generative-performance-benchmarking-temporal-understanding-on-videoinstruct | BT-Adapter | #12 | gpt-score: 2.34 |
| video-based-generative-performance-benchmarking-temporal-understanding-on-videoinstruct | BT-Adapter (zero-shot) | #14 | gpt-score: 2.13 |
| video-based-generative-performance-benchmarking-correctness-of-information-on-videoinstruct | BT-Adapter | #13 | gpt-score: 2.68 |
| video-based-generative-performance-benchmarking-correctness-of-information-on-videoinstruct | BT-Adapter (zero-shot) | #16 | gpt-score: 2.16 |
| video-based-generative-performance-benchmarking-detail-orientation-on-videoinstruct | BT-Adapter | #13 | gpt-score: 2.69 |
| video-based-generative-performance-benchmarking-detail-orientation-on-videoinstruct | BT-Adapter (zero-shot) | #16 | gpt-score: 2.46 |
| zero-shot-video-retrieval-on-didemo | BT-Adapter | #15 | text-to-video R@1: 35.6text-to-video R@5: 61.9… |
| zero-shot-video-retrieval-on-msr-vtt | BT-Adapter | #16 | text-to-video R@1: 40.9text-to-video R@5: 64.7… |
| video-based-generative-performance-benchmarking-on-videoinstruct | BT-Adapter | #18 | mean: 2.69Correctness of Information: 2.68Detail Orientation: 2.69… |
| video-based-generative-performance-benchmarking-on-videoinstruct | BT-Adapter (zero-shot) | #19 | mean: 2.46Correctness of Information: 2.16Detail Orientation: 2.46… |
| zeroshot-video-question-answer-on-activitynet-qa | BT-Adapter (zero-shot) | #20 | Accuracy: 46.1Confidence Score: 3.2 |
| zeroshot-video-question-answer-on-msvd-qa | BT-Adapter (zero-shot) | #23 | Accuracy: 67.0Confidence Score: 3.6 |
| zeroshot-video-question-answer-on-msvd-qa | BT-Adapter (zero-shot) | #24 | Accuracy: 67.0Confidence Score: 3.6 |
| zeroshot-video-question-answer-on-msrvtt-qa | BT-Adapter (zero-shot) | #25 | Accuracy: 51.2Confidence Score: 2.9 |
| zeroshot-video-question-answer-on-msrvtt-qa | BT-Adapter (zero-shot) | #26 | Accuracy: 51.2Confidence Score: 2.9 |