paper-with-me

홈 › Papers

Graph R-CNN for Scene Graph Generation

2018-08-01 · ECCV 2018 9 · Jianwei Yang, Jiasen Lu, Stefan Lee, Dhruv Batra, Devi Parikh

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. Our model contains a Relation Proposal Network (RePN) that efficiently deals with the quadratic number of potential relations between objects in an image. We also propose an attentional Graph Convolutional Network (aGCN) that effectively captures contextual information between objects and relations. Finally, we introduce a new evaluation metric that is more holistic and realistic than existing metrics. We report state-of-the-art performance on scene graph generation as evaluated using both existing and our proposed metrics.

📄 PDF Abstract BibTeX arXiv:1808.00191

Code (3)

ceyzaguirre4/NSM pytorch
jwyang/graph-rcnn.pytorch pytorch
microsoft/scene_graph_benchmark pytorch

Tasks

Graph GenerationScene Graph Generation

Similar Papers 제목 키워드 기반

MIGS: Meta Image Generation from Scene Graphs

2021-10-22 · Azade Farshad, Sabrina Musatian, Helisa Dhamo, Nassir Navab

Generation of images from scene graphs is a promising direction towards explicit scene generation and manipulation. However, the images generated from the scene graphs lack quality, which in part comes due to high diffic…

DiversityImage GenerationImage Generation from Scene GraphsMeta-Learning+1

Learning Visual Commonsense for Robust Scene Graph Generation

2020-06-17 · ECCV 2020 8 · Alireza Zareian, Zhecan Wang, Haoxuan You, Shih-Fu Chang

Scene graph generation models understand the scene through object and predicate recognition, but are prone to mistakes due to the challenges of perception in the wild. Perception errors often lead to nonsensical composit…

Graph GenerationScene Graph GenerationScene Understanding

Image Scene Graph Generation (SGG) Benchmark

2021-07-27 · Xiaotian Han, Jianwei Yang, Houdong Hu, Lei Zhang 외

There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection. Due to the …

AttributeGraph GenerationObjectobject-detection+4

Unconditional Scene Graph Generation

2021-08-12 · ICCV 2021 10 · Sarthak Garg, Helisa Dhamo, Azade Farshad, Sabrina Musatian 외

Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of no…

Anomaly DetectionGraph GenerationImage GenerationObject+1

Graph Canvas for Controllable 3D Scene Generation

2024-11-27 · Libin Liu, Shen Chen, Sen Jia, Jingzhe Shi 외

Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on…

In-Context LearningScene Generation