Accuracy (%): 86.34
Papers with Code · CC BY-SA 4.0
Natural Language Visual Grounding
논문
Accuracy (%): 83.0
Accuracy (%): 82.47
Accuracy (%): 75.1
Accuracy (%): 81.1
Accuracy (%): 47.4
Accuracy (%): 5.2
Accuracy (%): 28.6
Accuracy (%): 5.7
Accuracy (%): 73.0
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Accuracy (%): 5.2
Accuracy (%): 42.1
Accuracy (%): 53.4