Research map / Vision-language and multimodal / Human and embodied modeling
Synergistic Space-Vision Processing for Predicate Inference
Zhenhua Lei, Zefang Han, yu qiu
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 vision stream and cross-stream fusion to the space stream alone (ablation) | DS-Net · VG PredCls | mR@50/100: 32.5/34.7 -> 40.2/41.1 | Improved |
| add space stream and fusion to the vision stream alone (ablation) | DS-Net · VG PredCls | mR@50/100: 34.9/36.1 -> 40.2/41.1 | Improved |
| use proposed space stream instead of common space stream (ablation) | DS-Net · VG PredCls | mR@50/100: 38.1/39.3 -> 40.2/41.1 | Improved |
| use proposed vision stream instead of common vision stream (ablation) | DS-Net · VG PredCls | mR@50/100: 36.2/38.4 -> 40.2/41.1 | Improved |
| replace concatenation with cross-stream fusion (ablation) | DS-Net · VG PredCls | mR@50/100: 37.5/39.1 -> 40.2/41.1 | Improved |
| add space-to-vision fusion to vision-to-space fusion only (ablation) | DS-Net · VG PredCls | mR@50/100: 38.4/40.3 -> 40.2/41.1 | Improved |
| add vision-to-space fusion to space-to-vision fusion only (ablation) | DS-Net · VG PredCls | mR@50/100: 39.1/40.9 -> 40.2/41.1 | Improved |
| increase latent parts from 4 to 8 (ablation) | DS-Net · VG PredCls | mR@50/100: 37.4/38.9 -> 40.2/41.1 | Improved |
| increase latent parts from 8 to 14 (ablation) | DS-Net · VG PredCls | mR@50/100: 40.2/41.1 -> 39.9/41.0 | No clear effect |
| plug DS-Net into PENET | PENET · VG SGGen | mR@100: 14.5 -> 19.6 | Improved |
| plug DS-Net into RepSGG | RepSGG · VG SGGen | mR@100: 18.9 -> 21.7 | Improved |
| plug DS-Net into RA-SGG | RA-SGG · VG SGGen | mR@100: 17.1 -> 20.7 | Improved |
Closest papers by meaning
- Leveraging Predicate and Triplet Learning for Scene Graph Generation (CVPR 2024 · similarity 0.90)
- Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation (ICML 2025 · similarity 0.89)
- Panoptic Scene Graph Generation with Semantics-Prototype Learning (AAAI 2024 · similarity 0.89)
- Navigating the Unseen: Zero-shot Scene Graph Generation via Capsule-Based Equivariant Features (CVPR 2025 · similarity 0.88)
- DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation (CVPR 2024 · similarity 0.88)
- From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models (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.
