{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1511.06452","title":"Deep Metric Learning via Lifted Structured Feature Embedding","created":"2015-11-19","cited_by_count":449},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"1904.02239","title":"Hyperbolic Image Embeddings","created":"2019-04-03","cited_by_count":221},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180},{"id":"1804.01882","title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","created":"2018-04-03","cited_by_count":162},{"id":"1810.06546","title":"Poincar\\'e GloVe: Hyperbolic Word Embeddings","created":"2018-10-15","cited_by_count":156},{"id":"2008.01392","title":"Learning Visual Representations with Caption Annotations","created":"2020-08-04","cited_by_count":123},{"id":"1511.06361","title":"Order-Embeddings of Images and Language","created":"2015-11-19","cited_by_count":113},{"id":"2203.10833","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","created":"2022-03-21","cited_by_count":111},{"id":"2203.05898","title":"Hyperbolic Image Segmentation","created":"2022-03-11","cited_by_count":102},{"id":"1612.09161","title":"Learning Visual N-Grams from Web Data","created":"2016-12-29","cited_by_count":95},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89},{"id":"1805.06627","title":"Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures","created":"2018-05-17","cited_by_count":64},{"id":"2212.00653","title":"Hyperbolic Contrastive Learning for Visual Representations beyond Objects","created":"2022-12-01","cited_by_count":61},{"id":"1902.00913","title":"Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings","created":"2019-02-03","cited_by_count":49},{"id":"2110.14923","title":"Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones","created":"2021-10-28","cited_by_count":38},{"id":"2010.04831","title":"Improving Local Identifiability in Probabilistic Box Embeddings","created":"2020-10-09","cited_by_count":35},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32},{"id":"1707.07273","title":"Hierarchical Embeddings for Hypernymy Detection and Directionality","created":"2017-07-23","cited_by_count":19}],"next_cursor":null}