Research map / Vision-language and multimodal / Human and embodied modeling
Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
Haojun Jiang, Yuanze Lin, Dongchen Han, Shiji Song, Gao Huang
Check 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 |
|---|---|---|---|
| Generate pseudo region-query supervision using nouns, attributes, and spatial relationships without task annotations | Pseudo-Q visual grounding · RefCOCO val | top-1 accuracy (%): 56.02 vs. 39.21 | Improved |
| Generate pseudo region-query supervision without task annotations | Pseudo-Q visual grounding · RefCOCO+ testB | top-1 accuracy (%): 32.13 vs. 38.08 | Hurt |
| Generate pseudo region-query supervision without task annotations | Pseudo-Q visual grounding · ReferItGame | top-1 accuracy (%): 43.32 vs. 38.39 | Improved |
| Replace 12.01%, 20.68%, or 30.75% of manually labeled spatial-query examples with pseudo-samples | Fully supervised Pseudo-Q on RefCOCO · RefCOCO | top-1 accuracy: 12.01%, 20.68%, and 30.75% | No clear effect |
| Add attributes to nouns (ablation) | Pseudo-Q · RefCOCO | top-1 accuracy: 22.04 -> 31.30 | Improved |
| Add attributes to nouns (ablation) | Pseudo-Q · ReferItGame | top-1 accuracy: 27.91 -> 31.33 | Improved |
| Add spatial relationships to nouns (ablation) | Pseudo-Q · RefCOCO | top-1 accuracy: 22.04 -> 48.71; 26.67% | Improved |
| Add spatial relationships to nouns (ablation) | Pseudo-Q · ReferItGame | top-1 accuracy: 27.91 -> 39.26 | Improved |
| Add attributes and relationships to nouns (ablation) | Pseudo-Q · RefCOCO | top-1 accuracy: 22.04 -> 53.39 | Improved |
| Add attributes and relationships to nouns (ablation) | Pseudo-Q · ReferItGame | top-1 accuracy: 27.91 -> 40.37 | Improved |
| Add multi-level cross-modality attention (ablation) | Pseudo-Q with generated queries · RefCOCO | top-1 accuracy: +1.77% | Improved |
| Add multi-level cross-modality attention (ablation) | Pseudo-Q with generated queries · ReferItGame | top-1 accuracy: +1.35% | Improved |
Later papers that compared with this method
4 later accepted papers report Pseudo-Q as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · better on 1 of 1 shared result)
- Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding (CVPR 2024 · better on 11 of 11 shared results)
- Confidence-aware Pseudo-label Learning for Weakly Supervised Visual Grounding (ICCV 2023 · better on 2 of 2 shared results)
- Linking People across Text and Images Based on Social Relation Reasoning (AAAI 2023 · better on 0 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
- Referencing Where to Focus: Improving Visual Grounding with Referential Query (NeurIPS 2024 · similarity 0.91)
- Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding (CVPR 2025 · similarity 0.90)
- Improved Visual Grounding through Self-Consistent Explanations (CVPR 2024 · similarity 0.90)
- GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation (CVPR 2026 · similarity 0.90)
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.89)
- Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding (CVPR 2024 · similarity 0.89)
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.
