Research map / Vision-language and multimodal / Human and embodied modeling
Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance
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 |
|---|---|---|---|
| use UMGF instead of UMT | MNER · Twitter-2015 | overall F1: 73.18 -> 74.85† | Helped |
| use UMGF instead of UMT | MNER · Twitter-2017 | overall F1: 83.93 -> 85.51† | Helped |
| use UMGF instead of UMT | MNER · Twitter-2017c | overall F1: 82.43 -> 83.78† | Helped |
| use UMGF instead of UMT | MNER · Twitter-2017 → Twitter-2015 | overall F1: 64.13 -> 66.21† | Helped |
| use UMGF instead of UMT | MNER · Twitter-2015 → Twitter-2017 | overall F1: 60.87 -> 62.74† | Helped |
| add targeted visual guidance rather than average-segmented visual regions (ablation) | UMGF · Twitter-2015 | overall F1: 71.21 -> 74.85 | Helped |
| add targeted visual guidance rather than average-segmented visual regions (ablation) | UMGF · Twitter-2017 | overall F1: 83.26 -> 85.51 | Helped |
| add correlations among visual objects (ablation) | UMGF · Twitter-2015 | overall F1: 73.91 -> 74.85 | Helped |
| add correlations among visual objects (ablation) | UMGF · Twitter-2017 | overall F1: 84.18 -> 85.51 | Helped |
| use modality-specific rather than shared parameters (ablation) | UMGF · Twitter-2015 | overall F1: 73.64 -> 74.85 | Helped |
| use modality-specific rather than shared parameters (ablation) | UMGF · Twitter-2017 | overall F1: 84.61 -> 85.51 | Helped |
Closest papers by meaning
- Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation (AAAI 2025 · similarity 0.88)
- Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning (ICLR 2025 · similarity 0.88)
- Hierarchical Aligned Multimodal Learning for NER on Tweet Posts (AAAI 2024 · similarity 0.87)
- Beyond Entities: A Large-Scale Multi-Modal Knowledge Graph with Triplet Fact Grounding (AAAI 2024 · similarity 0.87)
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition (AAAI 2025 · similarity 0.86)
- Tackling Uncertain Correspondences for Multi-Modal Entity Alignment (NeurIPS 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.