{"list":"other","total":52,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"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":"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":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"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":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"1904.02239","title":"Hyperbolic Image Embeddings","created":"2019-04-03","cited_by_count":221},{"id":"1804.03329","title":"Representation Tradeoffs for Hyperbolic Embeddings","created":"2018-04-10","cited_by_count":206},{"id":"1810.00760","title":"Riemannian Adaptive Optimization Methods","created":"2018-10-01","cited_by_count":194},{"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":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"1511.06361","title":"Order-Embeddings of Images and Language","created":"2015-11-19","cited_by_count":113},{"id":"2203.05898","title":"Hyperbolic Image Segmentation","created":"2022-03-11","cited_by_count":102},{"id":"1412.6623","title":"Word Representations via Gaussian Embedding","created":"2014-12-20","cited_by_count":96},{"id":"1806.04313","title":"Embedding Text in Hyperbolic Spaces","created":"2018-06-12","cited_by_count":76},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74},{"id":"1805.06627","title":"Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures","created":"2018-05-17","cited_by_count":64},{"id":"1711.06420","title":"Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models","created":"2017-11-17","cited_by_count":53},{"id":"1704.02792","title":"Fine-graind Image Classification via Combining Vision and Language","created":"2017-04-10","cited_by_count":51},{"id":"2106.03306","title":"HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections","created":"2021-06-07","cited_by_count":47},{"id":"1306.6802","title":"Evaluation Measures for Hierarchical Classification: a unified view and novel approaches","created":"2013-06-28","cited_by_count":46},{"id":"1711.05435","title":"TorusE: Knowledge Graph Embedding on a Lie Group","created":"2017-11-15","cited_by_count":36},{"id":"2005.03847","title":"Tree! I am no Tree! I am a Low Dimensional Hyperbolic Embedding","created":"2020-05-08","cited_by_count":36},{"id":"2010.04831","title":"Improving Local Identifiability in Probabilistic Box Embeddings","created":"2020-10-09","cited_by_count":35},{"id":"1804.01720","title":"Finding beans in burgers: Deep semantic-visual embedding with localization","created":"2018-04-05","cited_by_count":28},{"id":"1710.05106","title":"CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning","created":"2017-10-14","cited_by_count":27},{"id":"1902.04335","title":"Hyperbolic Disk Embeddings for Directed Acyclic Graphs","created":"2019-02-12","cited_by_count":21},{"id":"1707.07273","title":"Hierarchical Embeddings for Hypernymy Detection and Directionality","created":"2017-07-23","cited_by_count":19},{"id":"1710.06371","title":"Specialising Word Vectors for Lexical Entailment","created":"2017-10-17","cited_by_count":18},{"id":"2401.07212","title":"HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval","created":"2024-01-14","cited_by_count":11},{"id":"2403.19881","title":"IME: Integrating Multi-curvature Shared and Specific Embedding for Temporal Knowledge Graph Completion","created":"2024-03-28","cited_by_count":9},{"id":"2502.17130","title":"Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space","created":"2025-02-24","cited_by_count":6}],"next_cursor":null}