Confidence Score: 3.6Accuracy: 46.4
Papers with Code · CC BY-SA 4.0
Zero-Shot Video Question Answer
This task present the results of Zeroshot Question Answer results on TGIF-QA dataset for LLM powered Video Conversational Models.
논문
Confidence Score: 3.3Accuracy: 47.5
Confidence Score: 3.5Accuracy: 58.4
Confidence Score: 3.2Accuracy: 46.1
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios
Confidence Score: 3.5Accuracy: 50.2
Confidence Score: 2.9Accuracy: 43.4
Confidence Score: 3.4Accuracy: 51.9
Confidence Score: 3.6Accuracy: 60.1
Confidence Score: 2.7Accuracy: 34.2
Confidence Score: 3.5Accuracy: 53.5
Accuracy: 46.3
Confidence Score: 3.1Accuracy: 45.7
Confidence Score: 3.3Accuracy: 49.1
Confidence Score: 3.7Accuracy: 60.9
Confidence Score: 3.6Accuracy: 60.7
Confidence Score: 3.5Accuracy: 59.2
Confidence Score: 3.3Accuracy: 50.9
Confidence Score: 3.7Accuracy: 61.6
Confidence Score: 3.5Accuracy: 58.9
Confidence Score: 2.7Accuracy: 35.2
Confidence Score: 3.3Accuracy: 50.1
Confidence Score: 1.1Accuracy: 12.4
Confidence Score: 3.3Accuracy: 45.3
Confidence Score: 2.2Accuracy: 26.5
Confidence Score: 3.6Accuracy: 50.6
Confidence Score: -Accuracy: 24.7