{"list":"other","total":82,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"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":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1605.09782","title":"Adversarial Feature Learning","created":"2016-05-31","cited_by_count":350},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"1907.02544","title":"Large Scale Adversarial Representation Learning","created":"2019-07-04","cited_by_count":239},{"id":"1605.07648","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","created":"2016-05-24","cited_by_count":216},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2111.12710","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","created":"2021-11-24","cited_by_count":204},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"1612.06370","title":"Learning Features by Watching Objects Move","created":"2016-12-19","cited_by_count":138},{"id":"2103.10022","title":"Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE","created":"2021-03-18","cited_by_count":106},{"id":"2203.05175","title":"MVP: Multimodality-guided Visual Pre-training","created":"2022-03-10","cited_by_count":92},{"id":"2208.06049","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","created":"2022-08-11","cited_by_count":69},{"id":"1812.00329","title":"Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning","created":"2018-12-02","cited_by_count":51},{"id":"1412.6056","title":"Unsupervised Learning of Spatiotemporally Coherent Metrics","created":"2014-12-18","cited_by_count":46},{"id":"2209.03917","title":"Exploring Target Representations for Masked Autoencoders","created":"2022-09-08","cited_by_count":46},{"id":"1708.02901","title":"Transitive Invariance for Self-supervised Visual Representation Learning","created":"2017-08-09","cited_by_count":37},{"id":"2205.14949","title":"HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling","created":"2022-05-30","cited_by_count":23},{"id":"2210.07224","title":"Exploring Long-Sequence Masked Autoencoders","created":"2022-10-13","cited_by_count":22}],"next_cursor":null}