{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"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":"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":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"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":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"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":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"1908.02486","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","created":"2019-08-07","cited_by_count":142},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45},{"id":"1807.10037","title":"Motion Feature Network: Fixed Motion Filter for Action Recognition","created":"2018-07-26","cited_by_count":34},{"id":"2303.11316","title":"Generative Semantic Segmentation","created":"2023-03-20","cited_by_count":32},{"id":"2207.12795","title":"Static and Dynamic Concepts for Self-supervised Video Representation Learning","created":"2022-07-26","cited_by_count":23},{"id":"2210.11035","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","created":"2022-10-20","cited_by_count":22},{"id":"2108.11575","title":"Shifted Chunk Transformer for Spatio-Temporal Representational Learning","created":"2021-08-26","cited_by_count":20},{"id":"2203.00307","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","created":"2022-03-01","cited_by_count":12}],"next_cursor":null}