{"list":"other","total":55,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1807.09937","title":"HiDDeN: Hiding Data With Deep Networks","created":"2018-07-26","cited_by_count":397},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2002.12416","title":"Learning in the Frequency Domain","created":"2020-02-27","cited_by_count":198},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158},{"id":"2206.10589","title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","created":"2022-06-21","cited_by_count":121},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"1908.05717","title":"Video Compression With Rate-Distortion Autoencoders","created":"2019-08-14","cited_by_count":97},{"id":"1811.06981","title":"Learned Video Compression","created":"2018-11-16","cited_by_count":89},{"id":"1703.10553","title":"Learning Convolutional Networks for Content-weighted Image Compression","created":"2017-03-30","cited_by_count":76},{"id":"2006.13560","title":"Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model","created":"2020-06-24","cited_by_count":67},{"id":"2002.03711","title":"Learning End-to-End Lossy Image Compression: A Benchmark","created":"2020-02-10","cited_by_count":60},{"id":"2004.09320","title":"Quantization Guided JPEG Artifact Correction","created":"2020-04-17","cited_by_count":57},{"id":"2209.07484","title":"Hydra Attention: Efficient Attention with Many Heads","created":"2022-09-15","cited_by_count":55},{"id":"1812.11690","title":"Deep Residual Learning in the JPEG Transform Domain","created":"2018-12-31","cited_by_count":44},{"id":"2210.09573","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2022-10-18","cited_by_count":41},{"id":"2207.05557","title":"LightViT: Towards Light-Weight Convolution-Free Vision Transformers","created":"2022-07-12","cited_by_count":40},{"id":"2203.03952","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","created":"2022-03-08","cited_by_count":28},{"id":"2011.09876","title":"DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation","created":"2020-11-19","cited_by_count":27},{"id":"1804.09869","title":"Learning for Video Compression","created":"2018-04-26","cited_by_count":26},{"id":"1906.09731","title":"Deep Residual Learning for Image Compression","created":"2019-06-24","cited_by_count":16},{"id":"1907.11503","title":"DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients","created":"2019-07-26","cited_by_count":11},{"id":"2205.12635","title":"MoCoViT: Mobile Convolutional Vision Transformer","created":"2022-05-25","cited_by_count":11},{"id":"1904.08408","title":"Fast object detection in compressed JPEG Images","created":"2019-04-16","cited_by_count":10},{"id":"1802.09371","title":"Autoencoder based image compression: can the learning be quantization independent?","created":"2018-02-23","cited_by_count":8},{"id":"2210.02995","title":"Compressed Vision for Efficient Video Understanding","created":"2022-10-06","cited_by_count":8},{"id":"1712.02313","title":"DCT-domain Deep Convolutional Neural Networks for Multiple JPEG Compression Classification","created":"2017-12-06","cited_by_count":7},{"id":"1907.10015","title":"Exploring Semantic Segmentation on the DCT Representation","created":"2019-07-23","cited_by_count":7},{"id":"2104.00185","title":"Less is More: Accelerating Faster Neural Networks Straight from JPEG","created":"2021-04-01","cited_by_count":7},{"id":"2210.01069","title":"Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration","created":"2022-10-03","cited_by_count":7},{"id":"2012.03357","title":"Rethinking FUN: Frequency-Domain Utilization Networks","created":"2020-12-06","cited_by_count":6},{"id":"2012.13726","title":"Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain","created":"2020-12-26","cited_by_count":5},{"id":"2207.07268","title":"Lightweight Vision Transformer with Cross Feature Attention","created":"2022-07-15","cited_by_count":5},{"id":"2208.06980","title":"Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers","created":"2022-08-15","cited_by_count":5},{"id":"2004.09226","title":"End-to-End Learning for Video Frame Compression with Self-Attention","created":"2020-04-20","cited_by_count":4},{"id":"1909.05638","title":"Faster and Accurate Classification for JPEG2000 Compressed Images in Networked Applications","created":"2019-09-04","cited_by_count":3},{"id":"2006.05732","title":"Object Detection in the DCT Domain: is Luminance the Solution?","created":"2020-06-10","cited_by_count":3},{"id":"2209.15006","title":"Effective Vision Transformer Training: A Data-Centric Perspective","created":"2022-09-29","cited_by_count":3},{"id":"2210.03861","title":"Towards Light Weight Object Detection System","created":"2022-10-08","cited_by_count":1}],"next_cursor":null}