Posted 2025-03-14Updated 2026-05-05Reviewa few seconds read (About 93 words) visitsFully Convolutional Scene Graph Generation One stage relation detection (detects objects and relations simultaneously). 这个模型受启发于 [[CenterNet]] 和 [[OpenPose Using Part Affinity Fields]]，通过添加一个新的用于生成RAF的卷积头来获取物体之间的关系。 具体RAF是如何定义的，以及如何训练(Loss)： Results Fully Convolutional Scene Graph Generationhttp://chen-yulin.github.io/2025/03/14/[OBS]Reconstruct Anything-Relation-(FCSGG) Fully Convolutional Scene Graph Generation/AuthorChen YulinPosted on2025-03-14Updated on2026-05-05Licensed under#Scene-graphVisual-RelationResearch-paperCVFPN
 Fully Convolutional Scene Graph Generation/Pasted_image_20250314123239.png)
 Fully Convolutional Scene Graph Generation/Pasted_image_20250317115153.png)
 Fully Convolutional Scene Graph Generation/Pasted_image_20250317115203.png)
 Fully Convolutional Scene Graph Generation/Pasted_image_20250317115216.png)
 Fully Convolutional Scene Graph Generation/Pasted_image_20250317121116.png)
 Fully Convolutional Scene Graph Generation/Pasted_image_20250317121142.png)
 Fully Convolutional Scene Graph Generation/Pasted_image_20250317121325.png)
