{"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"2103.10504","title":"UNETR: Transformers for 3D Medical Image Segmentation","created":"2021-03-18","cited_by_count":959},{"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":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2106.05735","title":"The Medical Segmentation Decathlon","created":"2021-06-10","cited_by_count":628},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2301.04856","title":"Multimodal Deep Learning","created":"2023-01-12","cited_by_count":258},{"id":"2103.03024","title":"CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation","created":"2021-03-04","cited_by_count":227},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"1602.01024","title":"On Deep Multi-View Representation Learning: Objectives and Optimization","created":"2016-02-02","cited_by_count":162},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134},{"id":"2106.06716","title":"DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation","created":"2021-06-12","cited_by_count":126},{"id":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109},{"id":"2104.06468","title":"ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration","created":"2021-04-13","cited_by_count":87},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64},{"id":"2108.09038","title":"Is it Time to Replace CNNs with Transformers for Medical Images?","created":"2021-08-20","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":"2107.05188","title":"TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation","created":"2021-07-12","cited_by_count":41},{"id":"2108.05305","title":"ConvNets vs. Transformers: Whose Visual Representations are More Transferable?","created":"2021-08-11","cited_by_count":35},{"id":"2205.10342","title":"Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)","created":"2022-05-20","cited_by_count":35},{"id":"2107.02104","title":"RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reporting","created":"2021-07-05","cited_by_count":34},{"id":"2201.04138","title":"Overview of the HECKTOR Challenge at MICCAI 2021: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT Images","created":"2022-01-11","cited_by_count":30},{"id":"2102.10446","title":"Squeeze-and-Excitation Normalization for Automated Delineation of Head and Neck Primary Tumors in Combined PET and CT Images","created":"2021-02-20","cited_by_count":20},{"id":"1711.00049","title":"Medical Image Segmentation Based on Multi-Modal Convolutional Neural Network: Study on Image Fusion Schemes","created":"2017-10-31","cited_by_count":6},{"id":"2104.08623","title":"Learning Fuzzy Clustering for SPECT/CT Segmentation via Convolutional Neural Networks","created":"2021-04-17","cited_by_count":3},{"id":"2202.07823","title":"Segmentation and Risk Score Prediction of Head and Neck Cancers in PET/CT Volumes with 3D U-Net and Cox Proportional Hazard Neural Networks","created":"2022-02-16","cited_by_count":2},{"id":"2212.10724","title":"Investigation of Network Architecture for Multimodal Head-and-Neck Tumor Segmentation","created":"2022-12-21","cited_by_count":1}],"next_cursor":null}