Research map / Graph learning / Knowledge and temporal graphs
Generating Triples With Adversarial Networks for Scene Graph Construction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use SG-GAN instead of the prior state-of-the-art method | Scene graph generation · Visual Genome, top 150 objects and 50 relations split | recall@50: 3.44 -> 6.84 | Helped |
| Use SG-GAN instead of the prior state-of-the-art method | Scene graph generation · Visual Genome, top 150 objects and 50 relations split | recall@100: 4.24 -> 8.95 | Helped |
| Expand the vocabulary and include attribute triples | SG-GAN · Visual Genome, custom split with 400 objects, 150 relations, and 150 attributes | recall@50 | Hurt |
| Expand the vocabulary and include attribute triples | SG-GAN · Visual Genome, custom split with 400 objects, 150 relations, and 150 attributes | recall@100 | Hurt |
Closest papers by meaning
- Image Generation From Scene Graphs (CVPR 2018 · similarity 0.93)
- Deep Generative Probabilistic Graph Neural Networks for Scene Graph Generation (AAAI 2020 · similarity 0.92)
- Scene Graph Generation by Iterative Message Passing (CVPR 2017 · similarity 0.91)
- From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models (CVPR 2024 · similarity 0.88)
- Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency (ICML 2024 · similarity 0.88)
- DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.