Research map / Graph learning / Knowledge and temporal graphs
Scene Graph Generation With External Knowledge and Image Reconstruction
Check 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 |
|---|---|---|---|
| Add ConceptNet knowledge refinement (ablation) | Baseline scene graph generator · VRD PhrDet | Rec@50: 25.57 -> 27.02 | Helped |
| Add image-generation supervision (ablation) | Baseline scene graph generator · VRD PhrDet | Rec@50: 25.57 -> 26.65 | Helped |
| Add both ConceptNet knowledge refinement and image-generation supervision (ablation) | Baseline scene graph generator · VRD SGGen | Rec@50: 18.16 -> 20.31 | Helped |
| Add ConceptNet knowledge refinement (ablation) | Baseline object detector · VRD object detection | mAP: 20.70 -> 22.26 | Helped |
| Add image-generation supervision (ablation) | Baseline object detector · VRD object detection | mAP: 20.70 -> 22.10 | Helped |
| Add image-generation supervision when object instances and corresponding relationships are randomly removed (ablation) | Baseline scene graph generator · Subsampled VRD | PhrDet Rec@50: 15.44 -> 24.07 | Helped |
| Train with image-generation supervision under missing object annotations (ablation) | KB-GAN · VRD versus subsampled VRD | PhrDet Rec@50: 27.39 -> 26.62 | Hurt |
| Train with image-generation supervision under missing object annotations (ablation) | KB-GAN · VRD versus subsampled VRD | SGGen Rec@50: 20.31 -> 19.78 | Hurt |
| Use KB-GAN instead of Factorizable Net | VG-MSDN · VG-MSDN SGGen | Rec@100: 16.47 -> 17.57 | Helped |
Closest papers by meaning
- Scene Graph Generation by Iterative Message Passing (CVPR 2017 · similarity 0.93)
- Iterative Scene Graph Generation (NeurIPS 2022 · similarity 0.91)
- DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation (CVPR 2024 · similarity 0.90)
- Adaptive Image-to-Video Scene Graph Generation via Knowledge Reasoning and Adversarial Learning (AAAI 2022 · similarity 0.90)
- Scene Graph-Grounded Image Generation (AAAI 2025 · similarity 0.89)
- Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency (ICML 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.