Research map / Vision-language and multimodal / Cross-modal learning
MERL: Multimodal Event Representation Learning in Heterogeneous Embedding Spaces
Linhai Zhang, Deyu Zhou, Yulan He, Zeng Yang
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 |
|---|---|---|---|
| train MERL with multimodal data instead of unimodal data (ablation) | MERL triple encoder · Multimodal Hard Similarity | accuracy: 44.3 -> 52.2 | Improved |
| train MERL with multimodal data instead of unimodal data (ablation) | MERL triple encoder · Transitive Sentence Similarity | Spearman's ρ: 0.61 -> 0.68 | Improved |
| train MERL with multimodal data instead of unimodal data (ablation) | MERL image encoder · Multimodal Hard Similarity | accuracy: 40.9 -> 47.0 | Improved |
| use MERL event embeddings in SGNN | SGNN · Script Event Prediction (MCNC) | accuracy: 52.45 -> 53.47 | Improved |
| combine SGNN(MERL), Additive, and PairLSTM predictions | Script event prediction · Script Event Prediction (MCNC) | accuracy: 54.93 -> 55.51 | Improved |
| use MERL rather than Hierarchical Order Embedding | Cross-modal event retrieval · Triple retrieval | recall@10: 61.0 -> 53.7 | Hurt |
| use MERL rather than Hierarchical Order Embedding | Cross-modal event retrieval · Image retrieval | recall@10: 56.2 -> 69.4 | Improved |
Later papers that compared with this method
3 later accepted papers report MERL as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- TAMER: A Tri-Modal Contrastive Alignment and Multi-Scale Embedding Refinement Framework for Zero-Shot ECG Diagnosis (CVPR 2026 · better on 4 of 5 shared results)
- Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners (ICML 2025 · better on 9 of 10 shared results)
- From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining (ICML 2025 · better on 6 of 6 shared results)
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
- EventGPT: Event Stream Understanding with Multimodal Large Language Models (CVPR 2025 · similarity 0.86)
- Beyond Grounding: Extracting Fine-Grained Event Hierarchies across Modalities (AAAI 2024 · similarity 0.85)
- Cross-modal Multi-task Learning for Multimedia Event Extraction (AAAI 2025 · similarity 0.85)
- Event-Equalized Dense Video Captioning (CVPR 2025 · similarity 0.84)
- EventLens: Event-Structure Reinforcement Learning for Video Understanding (NeurIPS 2026 · similarity 0.84)
- MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval (CVPR 2025 · similarity 0.84)
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.
