{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134},{"id":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"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},{"id":"2108.04539","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","created":"2021-08-10","cited_by_count":104},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90},{"id":"1903.11279","title":"Graph Convolution for Multimodal Information Extraction from Visually Rich Documents","created":"2019-03-27","cited_by_count":88},{"id":"2203.06947","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","created":"2022-03-14","cited_by_count":68},{"id":"2106.13488","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","created":"2021-06-25","cited_by_count":67},{"id":"2102.06732","title":"Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution","created":"2021-01-24","cited_by_count":64},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62},{"id":"2005.13118","title":"TRIE: End-to-End Text Reading and Information Extraction for Document Understanding","created":"2020-05-27","cited_by_count":61},{"id":"2009.11278","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","created":"2020-09-23","cited_by_count":59},{"id":"2002.08087","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","created":"2020-02-19","cited_by_count":53},{"id":"1810.13083","title":"GraphIE: A Graph-Based Framework for Information Extraction","created":"2018-10-31","cited_by_count":45},{"id":"2110.09753","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","created":"2021-10-19","cited_by_count":41},{"id":"2009.14457","title":"Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning","created":"2020-09-30","cited_by_count":21},{"id":"2104.08405","title":"LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding","created":"2021-04-16","cited_by_count":15}],"next_cursor":null}