{"list":"other","total":53,"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":"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"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":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"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":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2403.15378","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","created":"2024-03-22","cited_by_count":300},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"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":"1904.09658","title":"Probabilistic Face Embeddings","created":"2019-04-21","cited_by_count":173},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"2003.11339","title":"Data Uncertainty Learning in Face Recognition","created":"2020-03-25","cited_by_count":134},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118},{"id":"2105.03494","title":"The iWildCam 2021 Competition Dataset","created":"2021-05-07","cited_by_count":77},{"id":"1810.00319","title":"Modeling Uncertainty with Hedged Instance Embedding","created":"2018-09-30","cited_by_count":52},{"id":"2301.02560","title":"GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition","created":"2023-01-05","cited_by_count":50},{"id":"1912.01001","title":"View-Invariant Probabilistic Embedding for Human Pose","created":"2019-12-02","cited_by_count":47},{"id":"2305.18171","title":"Improved Probabilistic Image-Text Representations","created":"2023-05-29","cited_by_count":40},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37},{"id":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","cited_by_count":34},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29},{"id":"2302.02865","title":"Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs","created":"2023-02-06","cited_by_count":29},{"id":"2207.12576","title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","created":"2022-07-25","cited_by_count":20},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19},{"id":"2404.17507","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","created":"2024-04-26","cited_by_count":17},{"id":"1706.05111","title":"A Mixture Model for Learning Multi-Sense Word Embeddings","created":"2017-06-15","cited_by_count":12},{"id":"2004.04096","title":"Probabilistic embeddings for speaker diarization","created":"2020-04-06","cited_by_count":11}],"next_cursor":null}