{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"id":"1605.00459","title":"Multi30K: Multilingual English-German Image Descriptions","created":"2016-05-02","cited_by_count":250},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114},{"id":"2009.05387","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","created":"2020-09-11","cited_by_count":109},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95},{"id":"1805.08661","title":"COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval","created":"2018-05-22","cited_by_count":80},{"id":"1710.07177","title":"Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description","created":"2017-10-19","cited_by_count":76},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72},{"id":"2011.15124","title":"Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs","created":"2020-11-30","cited_by_count":71},{"id":"2104.00332","title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training","created":"2021-04-01","cited_by_count":64},{"id":"1807.00914","title":"Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing","created":"2018-07-02","cited_by_count":63},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59},{"id":"2010.15925","title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","created":"2020-10-29","cited_by_count":53},{"id":"1705.00823","title":"STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset","created":"2017-05-02","cited_by_count":47},{"id":"2012.15682","title":"A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters","created":"2020-12-31","cited_by_count":45},{"id":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41},{"id":"1601.03896","title":"Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures","created":"2016-01-15","cited_by_count":36},{"id":"1708.04390","title":"Fluency-Guided Cross-Lingual Image Captioning","created":"2017-08-15","cited_by_count":33},{"id":"2103.11920","title":"Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval","created":"2021-03-22","cited_by_count":28},{"id":"1707.06320","title":"Learning Visually Grounded Sentence Representations","created":"2017-07-19","cited_by_count":24},{"id":"1909.03493","title":"MULE: Multimodal Universal Language Embedding","created":"2019-09-08","cited_by_count":22},{"id":"2001.11453","title":"Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages","created":"2020-01-30","cited_by_count":22},{"id":"2005.03119","title":"Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting","created":"2020-05-06","cited_by_count":22},{"id":"2101.10044","title":"Cross-lingual Visual Pre-training for Multimodal Machine Translation","created":"2021-01-25","cited_by_count":19},{"id":"1707.07601","title":"Image Pivoting for Learning Multilingual Multimodal Representations","created":"2017-07-24","cited_by_count":17},{"id":"2106.09889","title":"GEM: A General Evaluation Benchmark for Multimodal Tasks","created":"2021-06-18","cited_by_count":16},{"id":"2002.00175","title":"UIT-ViIC: A Dataset for the First Evaluation on Vietnamese Image Captioning","created":"2020-02-01","cited_by_count":13},{"id":"1707.01736","title":"Cross-linguistic differences and similarities in image descriptions","created":"2017-07-06","cited_by_count":12},{"id":"1704.05347","title":"Baselines and test data for cross-lingual inference","created":"2017-04-18","cited_by_count":11},{"id":"1806.05645","title":"Grounded Textual Entailment","created":"2018-06-14","cited_by_count":10},{"id":"1910.00058","title":"Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations","created":"2019-09-30","cited_by_count":10},{"id":"2008.06376","title":"MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities","created":"2020-08-14","cited_by_count":10},{"id":"2103.01910","title":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","created":"2021-03-02","cited_by_count":10},{"id":"2106.01051","title":"Minimax and Neyman-Pearson Meta-Learning for Outlier Languages","created":"2021-06-02","cited_by_count":10},{"id":"2108.00061","title":"MTVR: Multilingual Moment Retrieval in Videos","created":"2021-07-30","cited_by_count":8},{"id":"2109.07622","title":"Towards Zero-shot Cross-lingual Image Retrieval and Tagging","created":"2021-09-15","cited_by_count":4},{"id":"1811.01115","title":"Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer","created":"2018-11-02","cited_by_count":1}],"next_cursor":null}