{"total":23,"rows":[{"id":"2111.02705","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24,"area":null},{"id":"2107.04419","title":"Form2Seq : A Framework for Higher-Order Form Structure Extraction","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16,"area":null},{"id":"2202.13562","title":"Name Your Style: An Arbitrary Artist-aware Image Style Transfer","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2205.12029","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification","created":"2022-05-24","cited_by_count":14,"area":null},{"id":"2106.14269","title":"Deep Learning for Technical Document Classification","created":"2021-06-27","cited_by_count":11,"area":null},{"id":"2107.04396","title":"Multi-Modal Association based Grouping for Form Structure Extraction","created":"2021-07-09","cited_by_count":6,"area":null},{"id":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2205.13530","title":"Semantic Parsing of Interpage Relations","created":"2022-05-26","cited_by_count":4,"area":null},{"id":"2305.06923","title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2106.13802","title":"Efficient Document Image Classification Using Region-Based Graph Neural Network","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2207.00748","title":"Sequence-aware multimodal page classification of Brazilian legal documents","created":"2022-07-02","cited_by_count":3,"area":null},{"id":"2101.01880","title":"On-Device Document Classification using multimodal features","created":"2021-01-06","cited_by_count":2,"area":null},{"id":"2211.06168","title":"Unimodal and Multimodal Representation Training for Relation Extraction","created":"2022-11-11","cited_by_count":2,"area":null},{"id":"2301.07502","title":"Multimodal Side-Tuning for Document Classification","created":"2023-01-16","cited_by_count":2,"area":null},{"id":"2412.02805","title":"STORM: Strategic Orchestration of Modalities for Rare Event Classification","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2104.05450","title":"Deep learning using Havrda-Charvat entropy for classification of pulmonary endomicroscopy","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2306.00750","title":"End-to-End Document Classification and Key Information Extraction using Assignment Optimization","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2110.02069","title":"OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis","created":"2021-10-01","cited_by_count":0,"area":null},{"id":"2410.09566","title":"Bridging Text and Image for Artist Style Transfer via Contrastive Learning","created":"2024-10-12","cited_by_count":0,"area":null},{"id":"2412.10155","title":"WordVIS: A Color Worth A Thousand Words","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2606.31956","title":"DEMUN: Fast and accurate discovery of music notation in very large collections","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}