{"total":20,"rows":[{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256,"area":null},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152,"area":null},{"id":"2202.13669","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","created":"2022-02-28","cited_by_count":107,"area":null},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91,"area":null},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62,"area":null},{"id":"2305.18721","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","created":"2023-05-30","cited_by_count":17,"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":"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":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","cited_by_count":5,"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":"2407.03830","title":"DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification","created":"2024-07-04","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":"2301.07502","title":"Multimodal Side-Tuning for Document Classification","created":"2023-01-16","cited_by_count":2,"area":null},{"id":"2304.12486","title":"Evaluating Adversarial Robustness on Document Image Classification","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2306.01359","title":"DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documents","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2311.03650","title":"Image Generation and Learning Strategy for Deep Document Forgery Detection","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2405.03660","title":"CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2405.14162","title":"Leveraging Semantic Segmentation Masks with Embeddings for Fine-Grained Form Classification","created":"2024-05-23","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":"2508.04233","title":"DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification","created":"2025-08-06","cited_by_count":0,"area":null}],"next_cursor":null}