{"list":"other","total":74,"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":"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"1908.08297","title":"EGNet:Edge Guidance Network for Salient Object Detection","created":"2019-08-22","cited_by_count":237},{"id":"1904.08739","title":"Cascaded Partial Decoder for Fast and Accurate Salient Object Detection","created":"2019-04-18","cited_by_count":216},{"id":"1904.09569","title":"A Simple Pooling-Based Design for Real-Time Salient Object Detection","created":"2019-04-21","cited_by_count":212},{"id":"2007.09062","title":"Multi-scale Interactive Network for Salient Object Detection","created":"2020-07-17","cited_by_count":212},{"id":"1611.04849","title":"Deeply supervised salient object detection with short connections","created":"2016-11-15","cited_by_count":196},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1503.08663","title":"Visual Saliency Based on Multiscale Deep Features","created":"2015-03-30","cited_by_count":185},{"id":"1911.11445","title":"F3Net: Fusion, Feedback and Focus for Salient Object Detection","created":"2019-11-26","cited_by_count":176},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"1904.09146","title":"Salient Object Detection in the Deep Learning Era: An In-Depth Survey","created":"2019-04-19","cited_by_count":164},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133},{"id":"1411.5752","title":"Hypercolumns for Object Segmentation and Fine-grained Localization","created":"2014-11-21","cited_by_count":128},{"id":"1903.00179","title":"Pyramid Feature Attention Network for Saliency detection","created":"2019-03-01","cited_by_count":128},{"id":"2007.08074","title":"Suppress and Balance: A Simple Gated Network for Salient Object Detection","created":"2020-07-16","cited_by_count":126},{"id":"2106.06716","title":"DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation","created":"2021-06-12","cited_by_count":126},{"id":"1807.09940","title":"Reverse Attention for Salient Object Detection","created":"2018-07-26","cited_by_count":113},{"id":"2008.11048","title":"Label Decoupling Framework for Salient Object Detection","created":"2020-08-25","cited_by_count":111},{"id":"2003.00651","title":"Global Context-Aware Progressive Aggregation Network for Salient Object Detection","created":"2020-03-02","cited_by_count":109},{"id":"1708.02001","title":"Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection","created":"2017-08-07","cited_by_count":93},{"id":"2104.00194","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","created":"2021-04-01","cited_by_count":93},{"id":"1908.07274","title":"Towards High-Resolution Salient Object Detection","created":"2019-08-20","cited_by_count":92},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2012.13093","title":"EDN: Salient Object Detection via Extremely-Downsampled Network","created":"2020-12-24","cited_by_count":64},{"id":"1603.01976","title":"Deep Contrast Learning for Salient Object Detection","created":"2016-03-07","cited_by_count":52},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52},{"id":"1812.10066","title":"Selectivity or Invariance: Boundary-aware Salient Object Detection","created":"2018-12-25","cited_by_count":48},{"id":"1708.02031","title":"Learning Uncertain Convolutional Features for Accurate Saliency Detection","created":"2017-08-07","cited_by_count":44},{"id":"2103.11731","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","created":"2021-03-22","cited_by_count":44},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"1604.05495","title":"Deep Saliency with Encoded Low level Distance Map and High Level Features","created":"2016-04-19","cited_by_count":23},{"id":"1610.01708","title":"A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection","created":"2016-10-06","cited_by_count":23},{"id":"2105.13865","title":"Recursive Contour Saliency Blending Network for Accurate Salient Object Detection","created":"2021-05-28","cited_by_count":20},{"id":"2004.09750","title":"MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation","created":"2020-04-21","cited_by_count":18},{"id":"2104.10127","title":"Generative Transformer for Accurate and Reliable Salient Object Detection","created":"2021-04-20","cited_by_count":18},{"id":"1903.12476","title":"DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection","created":"2019-03-28","cited_by_count":17},{"id":"1908.02460","title":"Edge-guided Non-local Fully Convolutional Network for Salient Object Detection","created":"2019-08-07","cited_by_count":16},{"id":"1903.10152","title":"SAC-Net: Spatial Attenuation Context for Salient Object Detection","created":"2019-03-25","cited_by_count":15},{"id":"2001.08057","title":"Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread","created":"2020-01-22","cited_by_count":13},{"id":"1909.04366","title":"Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection","created":"2019-09-10","cited_by_count":11}],"next_cursor":null}