Generation: 70.88
Papers with Code · CC BY-SA 4.0
Spatial Reasoning
논문
Total: 28.9Position-rel: 33.6Position-abs: 29.2Orientation-rel: 27.2
Generation: 36.07
Total: 36.2Position-rel: 49.4Position-abs: 28.4Orientation-rel: 44.2
Total: 27.2Position-rel: 30.9Position-abs: 24.5Orientation-rel: 28.3
Generation: 23.54
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Generation: 49.11
Total: 33.5Position-rel: 43.8Position-abs: 30.8Orientation-rel: 33.8
Total: 32.7Position-rel: 50.9Position-abs: 21.6Orientation-rel: 39.6
Generation: 35.19