Accuracy: 58.9Confidence Score: 3.3
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
Accuracy: 66.2Confidence Score: 3.6
Accuracy: 63.8Confidence Score: 3.5
Accuracy: 51.2Confidence Score: 2.9
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios
Accuracy: 62.1Confidence Score: 3.5
Accuracy: 55.0Confidence Score: 3.1
Accuracy: 71.5
Accuracy: 66.2Confidence Score: 4.0
Accuracy: 43.8Confidence Score: 2.7
Accuracy: 59.5Confidence Score: 3.6
Accuracy: 59.73
Accuracy: 52.7Confidence Score: 2.6
Accuracy: 54.1Confidence Score: 3.3
Accuracy: 55.3Confidence Score: 3.3
Accuracy: 64.3Confidence Score: 3.5
Accuracy: 56.8
Accuracy: 63.2Confidence Score: 3.4
Accuracy: 66.4Confidence Score: 3.7
Accuracy: 71.1
Accuracy: 67.1
Accuracy: 49.3Confidence Score: 2.8
Accuracy: 59.3Confidence Score: 3.3
Accuracy: 29.6Confidence Score: 1.8
Accuracy: 59.2Confidence Score: 3.5
Accuracy: 45.0Confidence Score: 2.5
Accuracy: 60.6Confidence Score: 3.6
Accuracy: 66.9
Accuracy: 60.5Confidence Score: 3.3