{"list":"other","total":103,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"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":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"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":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"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":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"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":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"1911.09435","title":"TEINet: Towards an Efficient Architecture for Video Recognition","created":"2019-11-21","cited_by_count":92},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"2011.07949","title":"RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning","created":"2020-10-27","cited_by_count":83},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"1912.00381","title":"Gate-Shift Networks for Video Action Recognition","created":"2019-12-01","cited_by_count":76},{"id":"2002.12177","title":"Evolving Losses for Unsupervised Video Representation Learning","created":"2020-02-26","cited_by_count":74},{"id":"1906.03349","title":"Video Modeling with Correlation Networks","created":"2019-06-07","cited_by_count":73},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"1711.09125","title":"Appearance-and-Relation Networks for Video Classification","created":"2017-11-24","cited_by_count":61},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61},{"id":"2006.15489","title":"Video Representation Learning with Visual Tempo Consistency","created":"2020-06-28","cited_by_count":57},{"id":"2106.11250","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","created":"2021-06-21","cited_by_count":56},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"2204.12260","title":"Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation","created":"2022-04-26","cited_by_count":52},{"id":"2204.12768","title":"Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training","created":"2022-04-27","cited_by_count":51},{"id":"2208.04164","title":"Understanding Masked Image Modeling via Learning Occlusion Invariant Feature","created":"2022-08-08","cited_by_count":50},{"id":"2206.04664","title":"On Data Scaling in Masked Image Modeling","created":"2022-06-09","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":"2001.05691","title":"Learning Spatiotemporal Features via Video and Text Pair Discrimination","created":"2020-01-16","cited_by_count":38},{"id":"2112.03612","title":"DCAN: Improving Temporal Action Detection via Dual Context Aggregation","created":"2021-12-07","cited_by_count":36},{"id":"2002.07442","title":"V4D:4D Convolutional Neural Networks for Video-level Representation Learning","created":"2020-02-18","cited_by_count":33}],"next_cursor":"100"}