{"list":"other","total":68,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"1905.00561","title":"Large-scale weakly-supervised pre-training for video action recognition","created":"2019-05-02","cited_by_count":130},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","created":"2016-11-07","cited_by_count":91},{"id":"1906.05571","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","created":"2019-06-13","cited_by_count":61},{"id":"1912.00998","title":"A Multigrid Method for Efficiently Training Video Models","created":"2019-12-02","cited_by_count":52},{"id":"2003.13042","title":"Omni-sourced Webly-supervised Learning for Video Recognition","created":"2020-03-29","cited_by_count":48},{"id":"1905.13209","title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","created":"2019-05-30","cited_by_count":46},{"id":"2112.07175","title":"Co-training Transformer with Videos and Images Improves Action Recognition","created":"2021-12-14","cited_by_count":41},{"id":"1510.00562","title":"Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks","created":"2015-10-02","cited_by_count":40},{"id":"2007.14937","title":"Learning Video Representations from Textual Web Supervision","created":"2020-07-29","cited_by_count":40},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"2007.12034","title":"AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification","created":"2020-07-23","cited_by_count":23},{"id":"2109.01696","title":"Revisiting 3D ResNets for Video Recognition","created":"2021-09-03","cited_by_count":10}],"next_cursor":null}