{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"2103.15306","title":"Checkerboard Context Model for Efficient Learned Image Compression","created":"2021-03-29","cited_by_count":202},{"id":"2111.12293","title":"PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization","created":"2021-11-24","cited_by_count":179},{"id":"2108.01390","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","created":"2021-08-03","cited_by_count":177},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153},{"id":"1704.00648","title":"Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations","created":"2017-04-03","cited_by_count":152},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1804.06919","title":"Video Compression through Image Interpolation","created":"2018-04-18","cited_by_count":143},{"id":"1809.10452","title":"Context-adaptive Entropy Model for End-to-end Optimized Image Compression","created":"2018-09-27","cited_by_count":143},{"id":"2007.03034","title":"Nonlinear Transform Coding","created":"2020-07-06","cited_by_count":136},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"2004.10290","title":"M-LVC: Multiple Frames Prediction for Learned Video Compression","created":"2020-04-21","cited_by_count":107},{"id":"2202.05492","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","created":"2022-02-11","cited_by_count":107},{"id":"1908.05717","title":"Video Compression With Rate-Distortion Autoencoders","created":"2019-08-14","cited_by_count":97},{"id":"2003.01966","title":"Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement","created":"2020-03-04","cited_by_count":90},{"id":"1811.06981","title":"Learned Video Compression","created":"2018-11-16","cited_by_count":89},{"id":"1904.03567","title":"Image and Video Compression with Neural Networks: A Review","created":"2019-04-07","cited_by_count":86},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2212.13824","title":"Multi-Realism Image Compression with a Conditional Generator","created":"2022-12-28","cited_by_count":80},{"id":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79},{"id":"2206.07307","title":"VCT: A Video Compression Transformer","created":"2022-06-15","cited_by_count":74},{"id":"1607.05006","title":"End-to-end optimization of nonlinear transform codes for perceptual quality","created":"2016-07-18","cited_by_count":73},{"id":"2104.14335","title":"ELF-VC: Efficient Learned Flexible-Rate Video Coding","created":"2021-04-29","cited_by_count":69},{"id":"2204.12997","title":"DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers","created":"2022-04-27","cited_by_count":65},{"id":"2107.01378","title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","created":"2021-07-03","cited_by_count":60},{"id":"2007.08563","title":"FTRANS: Energy-Efficient Acceleration of Transformers using FPGA","created":"2020-07-16","cited_by_count":54},{"id":"2104.05168","title":"Soft then Hard: Rethinking the Quantization in Neural Image Compression","created":"2021-04-12","cited_by_count":51},{"id":"2010.08321","title":"Learning Accurate Entropy Model with Global Reference for Image Compression","created":"2020-10-16","cited_by_count":45},{"id":"2008.09180","title":"Conditional Entropy Coding for Efficient Video Compression","created":"2020-08-20","cited_by_count":42},{"id":"2111.15127","title":"A Unified Pruning Framework for Vision Transformers","created":"2021-11-30","cited_by_count":40},{"id":"2107.12038","title":"Neural Video Compression using GANs for Detail Synthesis and Propagation","created":"2021-07-26","cited_by_count":36},{"id":"2104.00531","title":"Extending Neural P-frame Codecs for B-frame Coding","created":"2021-03-30","cited_by_count":30},{"id":"2112.09529","title":"End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression","created":"2021-12-17","cited_by_count":28},{"id":"1804.09869","title":"Learning for Video Compression","created":"2018-04-26","cited_by_count":26},{"id":"1903.04538","title":"A Machine Learning Dataset Prepared From the NASA Solar Dynamics Observatory Mission","created":"2019-03-11","cited_by_count":26},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20},{"id":"2401.14895","title":"MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer","created":"2024-01-26","cited_by_count":10},{"id":"2210.06478","title":"Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory","created":"2022-10-12","cited_by_count":8},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","cited_by_count":8},{"id":"2309.10799","title":"Multi-Context Dual Hyper-Prior Neural Image Compression","created":"2023-09-19","cited_by_count":6}],"next_cursor":null}