{"list":"other","total":139,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1804.03999","title":"Attention U-Net: Learning Where to Look for the Pancreas","created":"2018-04-11","cited_by_count":1435},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2201.01266","title":"Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images","created":"2022-01-04","cited_by_count":830},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1711.05225","title":"CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning","created":"2017-11-14","cited_by_count":461},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"2111.14791","title":"Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis","created":"2021-11-29","cited_by_count":422},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"2010.16056","title":"Generating Radiology Reports via Memory-driven Transformer","created":"2020-10-30","cited_by_count":368},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2103.04430","title":"TransBTS: Multimodal Brain Tumor Segmentation Using Transformer","created":"2021-03-07","cited_by_count":265},{"id":"2102.08005","title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","created":"2021-02-16","cited_by_count":258},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232},{"id":"2103.03024","title":"CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation","created":"2021-03-04","cited_by_count":227},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1711.08195","title":"On the Automatic Generation of Medical Imaging Reports","created":"2017-11-22","cited_by_count":216},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1507.06228","title":"Training Very Deep Networks","created":"2015-07-22","cited_by_count":173},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162},{"id":"1905.07799","title":"Adaptive Attention Span in Transformers","created":"2019-05-19","cited_by_count":149},{"id":"2008.07360","title":"A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context","created":"2020-08-07","cited_by_count":146},{"id":"2010.10042","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","created":"2020-10-20","cited_by_count":141},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","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":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"2109.07162","title":"MISSFormer: An Effective Medical Image Segmentation Transformer","created":"2021-09-15","cited_by_count":103},{"id":"2107.14293","title":"Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series","created":"2021-07-29","cited_by_count":96},{"id":"1907.01470","title":"Augmenting Self-attention with Persistent Memory","created":"2019-07-02","cited_by_count":93},{"id":"2103.05940","title":"TransMed: Transformers Advance Multi-modal Medical Image Classification","created":"2021-03-10","cited_by_count":86},{"id":"2107.08623","title":"LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation","created":"2021-07-19","cited_by_count":85},{"id":"1804.02391","title":"Learn To Pay Attention","created":"2018-04-06","cited_by_count":83},{"id":"2103.06104","title":"U-Net Transformer: Self and Cross Attention for Medical Image Segmentation","created":"2021-03-10","cited_by_count":81},{"id":"2111.03452","title":"Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports","created":"2021-11-04","cited_by_count":80},{"id":"1808.08127","title":"Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks","created":"2018-08-23","cited_by_count":76},{"id":"2004.03696","title":"SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation","created":"2020-04-07","cited_by_count":71},{"id":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71},{"id":"1710.07654","title":"Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning","created":"2017-10-20","cited_by_count":67},{"id":"2203.10095","title":"AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation","created":"2022-03-18","cited_by_count":65},{"id":"2107.05274","title":"TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation","created":"2021-07-12","cited_by_count":60},{"id":"2105.09511","title":"Medical Image Segmentation Using Squeeze-and-Expansion Transformers","created":"2021-05-20","cited_by_count":57},{"id":"2102.13645","title":"Convolution-Free Medical Image Segmentation using Transformers","created":"2021-02-26","cited_by_count":49},{"id":"2110.10403","title":"AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation","created":"2021-10-20","cited_by_count":48},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47},{"id":"1811.01328","title":"RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans","created":"2018-11-04","cited_by_count":41},{"id":"2107.05188","title":"TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation","created":"2021-07-12","cited_by_count":41},{"id":"2111.13300","title":"A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation","created":"2021-11-26","cited_by_count":41},{"id":"1708.02286","title":"Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification","created":"2017-08-03","cited_by_count":39},{"id":"2110.03864","title":"Boundary-aware Transformers for Skin Lesion Segmentation","created":"2021-10-08","cited_by_count":39},{"id":"2011.09763","title":"Attention-Based Transformers for Instance Segmentation of Cells in Microstructures","created":"2020-11-19","cited_by_count":38},{"id":"2107.02104","title":"RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reporting","created":"2021-07-05","cited_by_count":34},{"id":"1507.01053","title":"Describing Multimedia Content using Attention-based Encoder--Decoder Networks","created":"2015-07-04","cited_by_count":32},{"id":"2107.01682","title":"COVID-VIT: Classification of COVID-19 from CT chest images based on vision transformer models","created":"2021-07-04","cited_by_count":27},{"id":"2107.02467","title":"DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations","created":"2021-07-06","cited_by_count":27},{"id":"1911.11423","title":"Single Headed Attention RNN: Stop Thinking With Your Head","created":"2019-11-26","cited_by_count":26}],"next_cursor":"100"}