{"total":25,"rows":[{"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":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2110.06263","title":"Speech Summarization using Restricted Self-Attention","created":"2021-10-12","cited_by_count":23,"area":null},{"id":"2310.11612","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","created":"2023-10-17","cited_by_count":20,"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":"2401.09899","title":"Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations","created":"2024-01-18","cited_by_count":13,"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":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12,"area":null},{"id":"2207.07934","title":"Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model","created":"2022-07-16","cited_by_count":11,"area":null},{"id":"2306.00379","title":"Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"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":"2208.11671","title":"Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model","created":"2022-08-24","cited_by_count":5,"area":null},{"id":"2209.01638","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","created":"2022-09-04","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":"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":"2312.06950","title":"READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2211.07210","title":"Grafting Pre-trained Models for Multimodal Headline Generation","created":"2022-11-14","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":"2202.10967","title":"Learning Cluster Patterns for Abstractive Summarization","created":"2022-02-22","cited_by_count":0,"area":null},{"id":"2207.02663","title":"Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands","created":"2022-07-06","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":"2308.11351","title":"MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2509.13474","title":"Semantic-Enhanced Cross-Modal Place Recognition for Robust Robot Localization","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2603.29901","title":"Less Is More? Selective Visual Attention to High-Importance Regions for Multimodal Radiology Summarization","created":"2026-03-31","cited_by_count":0,"area":null}],"next_cursor":null}