{"total":37,"rows":[{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2101.06072","title":"Video Summarization Using Deep Neural Networks: A Survey","created":"2021-01-15","cited_by_count":85,"area":null},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32,"area":null},{"id":"2109.05199","title":"A Survey on Multi-modal Summarization","created":"2021-09-11","cited_by_count":26,"area":null},{"id":"2104.12714","title":"Focused Attention Improves Document-Grounded Generation","created":"2021-04-26","cited_by_count":24,"area":null},{"id":"2110.06263","title":"Speech Summarization using Restricted Self-Attention","created":"2021-10-12","cited_by_count":23,"area":null},{"id":"2105.09601","title":"See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization","created":"2021-05-20","cited_by_count":18,"area":null},{"id":"2112.12072","title":"Hierarchical Cross-Modality Semantic Correlation Learning Model for Multimodal Summarization","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2109.05160","title":"StreamHover: Livestream Transcript Summarization and Annotation","created":"2021-09-11","cited_by_count":15,"area":null},{"id":"2212.07672","title":"Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization","created":"2022-12-15","cited_by_count":14,"area":null},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","cited_by_count":12,"area":null},{"id":"2402.11414","title":"Fine-grained and Explainable Factuality Evaluation for Multimodal Summarization","created":"2024-02-18","cited_by_count":10,"area":null},{"id":"2306.13968","title":"Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents","created":"2023-06-24","cited_by_count":7,"area":null},{"id":"2211.02580","title":"Evaluating and Improving Factuality in Multimodal Abstractive Summarization","created":"2022-11-04","cited_by_count":6,"area":null},{"id":"2502.07096","title":"Lotus: Creating Short Videos From Long Videos With Abstractive and Extractive Summarization","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2306.09922","title":"Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2401.06806","title":"AugSumm: towards generalizable speech summarization using synthetic labels from large language model","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2504.08024","title":"Summarizing Speech: A Comprehensive Survey","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2305.14652","title":"Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2407.02005","title":"An End-to-End Speech Summarization Using Large Language Model","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2203.06671","title":"Summarizing a virtual robot's past actions in natural language","created":"2022-03-13","cited_by_count":3,"area":null},{"id":"2408.07277","title":"Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2204.08352","title":"MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video Summarization","created":"2022-04-18","cited_by_count":2,"area":null},{"id":"2204.12681","title":"Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2302.09934","title":"CISum: Learning Cross-modality Interaction to Enhance Multimodal Semantic Coverage for Multimodal Summarization","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2202.08138","title":"When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs","created":"2022-02-16","cited_by_count":1,"area":null},{"id":"2305.04824","title":"Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2403.17727","title":"FastPerson: Enhancing Video Learning through Effective Video Summarization that Preserves Linguistic and Visual Contexts","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2410.04449","title":"Video Summarization Techniques: A Comprehensive Review","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2303.04361","title":"Sample Efficient Multimodal Semantic Augmentation for Incremental Summarization","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2307.02716","title":"CFSum: A Coarse-to-Fine Contribution Network for Multimodal Summarization","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2508.17199","title":"MMCIG: Multimodal Cover Image Generation for Text-only Documents and Its Dataset Construction via Pseudo-labeling","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2510.05652","title":"SD-MVSum: Script-Driven Multimodal Video Summarization Method and Datasets","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2608.10359","title":"VoxSumm: A Multilingual Corpus of Long-Form Spoken News for Joint Summarization and Translation","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}