Research map / Graph learning / Knowledge and temporal graphs
APT: Towards Universal Scene Graph Generation via Plug-in Adaptive Prompt Tuning
Ruikun Luo, Changwei Gu, Jing Yang, Yuan Gao, Jieming Yang, Song Wu, Hai Jin, Xiaoyu Xia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 APT prompts | EGTR · VG PredCls | mR@100: 38.2 -> 40.1 | Improved |
| add APT prompts | LLM4SGG · VG PredCls | mR@100: 39.1 -> 42.2 | Improved |
| add APT prompts | DRM · VG PredCls | mR@100: 19.2 -> 21.9 | Improved |
| add APT prompts | RA-SGG · VG PredCls | mR@100: 19.8 -> 20.2 | Improved |
| add APT prompts | SDSGG · VG open-vocabulary Novel | mR@50: 25.2 -> 26.7 | Improved |
| add APT prompts | OvSGTR · VG open-vocabulary Novel | mR@50: 13.5 -> 14.3 | Improved |
| add Detection Prompt only (ablation) | PE-Net · VG PredCls | mR@100: 33.8 -> 32.6 | Hurt |
| add Relation Prompt only (ablation) | PE-Net · VG PredCls | mR@100: 33.8 -> 36.4 | Improved |
| add both prompts (full APT) rather than R-Prompt only (ablation) | PE-Net · VG PredCls | mR@100: 36.4 -> 39.1 | Improved |
| add Relational Context Gating (ablation) | SDSGG · VG open-vocabulary Novel | mR@50: 25.2 -> 26.7 | Improved |
| add Basis Prompt Synthesis on top of RCG (ablation) | SDSGG · VG open-vocabulary Novel | mR@50: 26.7 -> 29.0 | Improved |
| add Feature Refinement & Fusion (full CGP) (ablation) | SDSGG · VG open-vocabulary Novel | mR@50: 29.0 -> 31.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SGTR — SGTR: End-to-End Scene Graph Generation With Transformer (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models (CVPR 2024 · similarity 0.91)
- Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation (AAAI 2025 · similarity 0.91)
- Scene Graph Generation with Role-Playing Large Language Models (NeurIPS 2024 · similarity 0.91)
- Universal Scene Graph Generation (CVPR 2025 · similarity 0.91)
- Adaptive Visual Scene Understanding: Incremental Scene Graph Generation (NeurIPS 2024 · similarity 0.90)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (CVPR 2025 · similarity 0.90)
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.
