{"total":50,"rows":[{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2305.13507","title":"Multimodal Automated Fact-Checking: A Survey","created":"2023-05-22","cited_by_count":53,"area":null},{"id":"2311.09562","title":"TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction","created":"2023-11-16","cited_by_count":28,"area":null},{"id":"2109.12776","title":"Joint Multimedia Event Extraction from Video and Article","created":"2021-09-27","cited_by_count":19,"area":null},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","cited_by_count":19,"area":null},{"id":"2112.15280","title":"What is Event Knowledge Graph: A Survey","created":"2021-12-31","cited_by_count":19,"area":null},{"id":"2101.04922","title":"EventPlus: A Temporal Event Understanding Pipeline","created":"2021-01-13","cited_by_count":17,"area":null},{"id":"2401.03082","title":"UMIE: Unified Multimodal Information Extraction with Instruction Tuning","created":"2024-01-05","cited_by_count":17,"area":null},{"id":"2104.03762","title":"Video Question Answering with Phrases via Semantic Roles","created":"2021-04-08","cited_by_count":13,"area":null},{"id":"2107.02126","title":"A Survey on Deep Learning Event Extraction: Approaches and Applications","created":"2021-07-05","cited_by_count":12,"area":null},{"id":"2408.08074","title":"A Survey on Integrated Sensing, Communication, and Computation","created":"2024-08-15","cited_by_count":12,"area":null},{"id":"2306.08966","title":"Training Multimedia Event Extraction With Generated Images and Captions","created":"2023-06-15","cited_by_count":11,"area":null},{"id":"2202.08063","title":"Information Extraction in Low-Resource Scenarios: Survey and Perspective","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2211.01781","title":"Video Event Extraction via Tracking Visual States of Arguments","created":"2022-11-03","cited_by_count":8,"area":null},{"id":"2307.03153","title":"MultiVENT: Multilingual Videos of Events with Aligned Natural Text","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2403.02586","title":"Improving Event Definition Following For Zero-Shot Event Detection","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2404.01679","title":"Event Detection from Social Media for Epidemic Prediction","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2410.18393","title":"SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness","created":"2024-10-24","cited_by_count":7,"area":null},{"id":"2505.06303","title":"Collaborative Multi-LoRA Experts with Achievement-based Multi-Tasks Loss for Unified Multimodal Information Extraction","created":"2025-05-08","cited_by_count":7,"area":null},{"id":"2302.13311","title":"Understanding Social Media Cross-Modality Discourse in Linguistic Space","created":"2023-02-26","cited_by_count":6,"area":null},{"id":"2310.03017","title":"Multimodal Question Answering for Unified Information Extraction","created":"2023-10-04","cited_by_count":6,"area":null},{"id":"2406.12420","title":"MMUTF: Multimodal Multimedia Event Argument Extraction with Unified Template Filling","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2404.08949","title":"Multimodal Cross-Document Event Coreference Resolution Using Linear Semantic Transfer and Mixed-Modality Ensembles","created":"2024-04-13","cited_by_count":4,"area":null},{"id":"2108.12899","title":"Fine-Grained Chemical Entity Typing with Multimodal Knowledge Representation","created":"2021-08-29","cited_by_count":3,"area":null},{"id":"2206.07207","title":"Beyond Grounding: Extracting Fine-Grained Event Hierarchies Across Modalities","created":"2022-06-14","cited_by_count":3,"area":null},{"id":"2502.17394","title":"SNaRe: Domain-aware Data Generation for Low-Resource Event Detection","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2503.03303","title":"SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2509.12876","title":"Benchmarking and Improving LVLMs on Event Extraction from Multimedia Documents","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2205.04402","title":"Detecting the Role of an Entity in Harmful Memes: Techniques and Their Limitations","created":"2022-05-09","cited_by_count":2,"area":null},{"id":"2210.12582","title":"Language Model Pre-Training with Sparse Latent Typing","created":"2022-10-23","cited_by_count":2,"area":null},{"id":"2404.04763","title":"GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2305.03517","title":"Few-shot Domain-Adaptive Visually-fused Event Detection from Text","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2306.10068","title":"Artificial Intelligence for Emergency Response","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2310.08204","title":"STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2312.03093","title":"RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2406.14075","title":"EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2504.21372","title":"Retrieval-Enhanced Few-Shot Prompting for Speech Event Extraction","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2505.10836","title":"Multimodal Event Detection: Current Approaches and Defining the New Playground through LLMs and VLMs","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2301.03410","title":"In Defense of Structural Symbolic Representation for Video Event-Relation Prediction","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2410.09418","title":"Beyond Exact Match: Semantically Reassessing Event Extraction by Large Language Models","created":"2024-10-12","cited_by_count":0,"area":null},{"id":"2508.05028","title":"Evaluation of Finetuned LLMs in AMR Parsing","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2602.13748","title":"RMPL: Relation-aware Multi-task Progressive Learning with Stage-wise Training for Multimedia Event Extraction","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2606.18780","title":"SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.26775","title":"Evaluation Pitfalls and Challenges in Multimedia Event Extraction","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.23235","title":"A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.29230","title":"EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.12580","title":"CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.17113","title":"Calibrated Typed Decisions for Entity, Relation, and Event Extraction","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}