Scene Graph Generation
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
Greatest papers with code
Graph R-CNN for Scene Graph Generation
ECCV 2018
• jwyang/graph-rcnn.pytorch
• 
We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images.
Scene Graph Generation from Objects, Phrases and Region Captions
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information.
GRAPH GENERATION OBJECT DETECTION SCENE GRAPH GENERATION SCENE UNDERSTANDING
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
ECCV 2018
• yikang-li/FactorizableNet
•
Generating scene graph to describe all the relations inside an image gains increasing interests these years.
SOTA for Scene Graph Generation on VRD
Pixels to Graphs by Associative Embedding
NeurIPS 2017
• nexusapoorvacus/DeepVariationStructuredRL
•
Graphs are a useful abstraction of image content.
Scene Graph Generation by Iterative Message Passing
CVPR 2017
• shikorab/SceneGraph
• 
In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image.
Knowledge-Embedded Routing Network for Scene Graph Generation
More specifically, we show that the statistical correlations between objects appearing in images and their relationships, can be explicitly represented by a structured knowledge graph, and a routing mechanism is learned to propagate messages through the graph to explore their interactions.
The Limited Multi-Label Projection Layer
• locuslab/lml
•
We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems.
Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning
• paulgay/VGfM
•
Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships.