Research map / Vision-language and multimodal / Human and embodied modeling
Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
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 |
|---|---|---|---|
| add visual consistency to language consistency (ablation) | KAC Net · Flickr30K Entities | accuracy (%): 34.31 -> 38.71 | Helped |
| add visual consistency to language consistency (ablation) | KAC Net · Referit Game | accuracy (%): 13.97 -> 15.83 | Helped |
| replace Hard KBP with Soft KBP (ablation) | KAC Net · Flickr30K Entities | accuracy (%): 37.41 -> 38.71 | Helped |
| replace Hard KBP with Soft KBP (ablation) | KAC Net · Referit Game | accuracy (%): 14.68 -> 15.83 | Helped |
| add a Soft KBP gate (ablation) | visual consistency branch · Flickr30K Entities | accuracy (%): 28.58 -> 30.60 | Helped |
| add a Soft KBP gate (ablation) | language consistency branch · Flickr30K Entities | accuracy (%): 32.17 -> 34.31 | Helped |
| add knowledge from MSCOCO classification (ablation) | KAC Net · Flickr30K Entities | accuracy (%): 36.14 -> 38.71 | Helped |
| add knowledge from MSCOCO classification (ablation) | KAC Net · Referit Game | accuracy (%): 13.38 -> 15.83 | Helped |
| combine visual and language consistency (ablation) | grounding model · Flickr30K Entities, clothing phrases | accuracy (%): 9.02 -> 7.63 | Hurt |
Closest papers by meaning
- Look Around Before Locating: Considering Content and Structure Information for Visual Grounding (AAAI 2025 · similarity 0.89)
- Momentum Pseudo-Labeling for Weakly Supervised Phrase Grounding (AAAI 2025 · similarity 0.88)
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.88)
- Referencing Where to Focus: Improving Visual Grounding with Referential Query (NeurIPS 2024 · similarity 0.87)
- Improved Visual Grounding through Self-Consistent Explanations (CVPR 2024 · similarity 0.87)
- Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network (AAAI 2025 · similarity 0.87)
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.