{"list":"other","total":86,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"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":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"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":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2108.01390","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","created":"2021-08-03","cited_by_count":177},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"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":"1809.00916","title":"OCNet: Object Context Network for Scene Parsing","created":"2018-09-04","cited_by_count":140},{"id":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131},{"id":"2007.04825","title":"Fast Transformers with Clustered Attention","created":"2020-07-09","cited_by_count":123},{"id":"2201.08371","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","created":"2022-01-20","cited_by_count":116},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"2007.04269","title":"SegFix: Model-Agnostic Boundary Refinement for Segmentation","created":"2020-07-08","cited_by_count":97},{"id":"1807.10174","title":"Superpixel Sampling Networks","created":"2018-07-26","cited_by_count":79},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66},{"id":"2202.12015","title":"Learning to Merge Tokens in Vision Transformers","created":"2022-02-24","cited_by_count":65},{"id":"2112.12782","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","created":"2021-12-23","cited_by_count":55},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52},{"id":"2010.14819","title":"Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets","created":"2020-10-28","cited_by_count":49},{"id":"2010.05315","title":"SMYRF: Efficient Attention using Asymmetric Clustering","created":"2020-10-11","cited_by_count":43},{"id":"2209.13802","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","created":"2022-09-28","cited_by_count":35},{"id":"2208.07220","title":"PatchDropout: Economizing Vision Transformers Using Patch Dropout","created":"2022-08-10","cited_by_count":28},{"id":"2010.04879","title":"Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework","created":"2020-10-10","cited_by_count":27},{"id":"1912.10178","title":"DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration","created":"2019-12-21","cited_by_count":24},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15},{"id":"2201.00043","title":"Multi-Dimensional Model Compression of Vision Transformer","created":"2021-12-31","cited_by_count":13},{"id":"2111.13677","title":"SWAT: Spatial Structure Within and Among Tokens","created":"2021-11-26","cited_by_count":4}],"next_cursor":null}