Research map / Vision-language and multimodal / Human and embodied modeling
MNER-QG: An End-to-End MRC Framework for Multimodal Named Entity Recognition with Query 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 |
|---|---|---|---|
| Jointly train query grounding with MNER instead of training FA-VG separately | MNER-QG · Twitter2015 test | Accu@0.5: 50.83 -> 54.86 | Helped |
| Jointly train query grounding with MNER instead of training FA-VG separately | MNER-QG · Twitter2017 test | Accu@0.5: 56.03 -> 58.49 | Helped |
| Use manual bounding-box annotations instead of weak supervision | MNER-QG · Twitter2015 test | Accu@0.5: 54.86 -> 67.41 | Helped |
| Use manual bounding-box annotations instead of weak supervision | MNER-QG · Twitter2017 test | Accu@0.5: 58.49 -> 73.53 | Helped |
| Add image input and joint query grounding to the text-only model | MNER-QG · Twitter2015 test | F1: 72.74 -> 74.70 | Helped |
| Add image input and joint query grounding to the text-only model | MNER-QG · Twitter2017 test | F1: 85.55 -> 86.94 | Helped |
| Add QG loss (ablation) | MNER-QG · Twitter2015 test | F1: 73.99 -> 74.70 | Helped |
| Add QG loss (ablation) | MNER-QG · Twitter2017 test | F1: 86.32 -> 86.94 | Helped |
| Add ED loss (ablation) | MNER-QG · Twitter2015 test | F1: 74.23 -> 74.70 | Helped |
| Add ED loss (ablation) | MNER-QG · Twitter2017 test | F1: 86.53 -> 86.94 | Helped |
| Add both QG and ED losses (ablation) | MNER-QG · Twitter2015 test | F1: 73.57 -> 74.70 | Helped |
| Add both QG and ED losses (ablation) | MNER-QG · Twitter2017 test | F1: 86.02 -> 86.94 | Helped |
Closest papers by meaning
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition (AAAI 2025 · similarity 0.92)
- Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach (NeurIPS 2024 · similarity 0.89)
- Hierarchical Aligned Multimodal Learning for NER on Tweet Posts (AAAI 2024 · similarity 0.89)
- Prototype-Guided Multimodal Relation Extraction based on Entity Attributes (AAAI 2025 · similarity 0.87)
- A Dual-Way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking (AAAI 2024 · similarity 0.87)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.86)
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.