{"list":"other","total":69,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"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":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"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":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2111.12293","title":"PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization","created":"2021-11-24","cited_by_count":179},{"id":"1702.07811","title":"Adaptive Neural Networks for Efficient Inference","created":"2017-02-25","cited_by_count":163},{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163},{"id":"1808.05779","title":"Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss","created":"2018-08-17","cited_by_count":160},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2206.10589","title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","created":"2022-06-21","cited_by_count":121},{"id":"1612.02297","title":"Spatially Adaptive Computation Time for Residual Networks","created":"2016-12-07","cited_by_count":118},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"2010.05300","title":"Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification","created":"2020-10-11","cited_by_count":100},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"1908.06294","title":"Improved Techniques for Training Adaptive Deep Networks","created":"2019-08-17","cited_by_count":66},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64},{"id":"2003.10027","title":"Dynamic ReLU","created":"2020-03-22","cited_by_count":55},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44},{"id":"2204.02557","title":"MixFormer: Mixing Features across Windows and Dimensions","created":"2022-04-06","cited_by_count":43},{"id":"1907.06627","title":"Batch-Shaping for Learning Conditional Channel Gated Networks","created":"2019-07-15","cited_by_count":42},{"id":"2112.14238","title":"AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition","created":"2021-12-28","cited_by_count":37},{"id":"2104.04382","title":"CondenseNet V2: Sparse Feature Reactivation for Deep Networks","created":"2021-04-09","cited_by_count":34},{"id":"2210.06223","title":"Latency-aware Spatial-wise Dynamic Networks","created":"2022-10-12","cited_by_count":25},{"id":"2209.13465","title":"AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition","created":"2022-09-27","cited_by_count":18}],"next_cursor":null}