{"list":"other","total":71,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"1911.06667","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","created":"2019-11-15","cited_by_count":201},{"id":"1902.04049","title":"MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation","created":"2019-02-11","cited_by_count":195},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"2001.00309","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","created":"2020-01-02","cited_by_count":145},{"id":"1611.07709","title":"Fully Convolutional Instance-aware Semantic Segmentation","created":"2016-11-23","cited_by_count":123},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"2007.00047","title":"A Survey on Instance Segmentation: State of the art","created":"2020-06-28","cited_by_count":85},{"id":"1506.06204","title":"Learning to Segment Object Candidates","created":"2015-06-20","cited_by_count":79},{"id":"2007.08921","title":"Boundary-preserving Mask R-CNN","created":"2020-07-17","cited_by_count":74},{"id":"1604.08202","title":"Amodal Instance Segmentation","created":"2016-04-27","cited_by_count":63},{"id":"1712.08273","title":"Recurrent Pixel Embedding for Instance Grouping","created":"2017-12-22","cited_by_count":58},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46},{"id":"2108.11510","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","created":"2021-08-25","cited_by_count":43},{"id":"1703.10277","title":"Semantic Instance Segmentation via Deep Metric Learning","created":"2017-03-30","cited_by_count":37},{"id":"2210.06323","title":"AISFormer: Amodal Instance Segmentation with Transformer","created":"2022-10-12","cited_by_count":35},{"id":"1811.05588","title":"YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers","created":"2018-11-14","cited_by_count":34},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34},{"id":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25},{"id":"1711.07618","title":"S4Net: Single Stage Salient-Instance Segmentation","created":"2017-11-21","cited_by_count":23},{"id":"2204.09151","title":"Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles","created":"2022-04-19","cited_by_count":20},{"id":"2206.12972","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","created":"2022-06-26","cited_by_count":19},{"id":"2204.01244","title":"Dynamic Focus-aware Positional Queries for Semantic Segmentation","created":"2022-04-04","cited_by_count":16},{"id":"1912.01954","title":"EmbedMask: Embedding Coupling for One-stage Instance Segmentation","created":"2019-12-04","cited_by_count":15},{"id":"2210.02578","title":"AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation","created":"2022-10-05","cited_by_count":14},{"id":"1811.11849","title":"Non-Volume Preserving-based Fusion to Group-Level Emotion Recognition on Crowd Videos","created":"2018-11-28","cited_by_count":13},{"id":"1811.11080","title":"MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices","created":"2018-11-27","cited_by_count":12},{"id":"2205.10738","title":"OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation","created":"2022-05-22","cited_by_count":12},{"id":"2210.04615","title":"EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification","created":"2022-10-07","cited_by_count":12},{"id":"2110.11474","title":"AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation","created":"2021-10-21","cited_by_count":11},{"id":"1606.02254","title":"Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines","created":"2016-06-07","cited_by_count":10},{"id":"2201.05905","title":"SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data","created":"2022-01-15","cited_by_count":10},{"id":"2309.13550","title":"I-AI: A Controllable & Interpretable AI System for Decoding Radiologists' Intense Focus for Accurate CXR Diagnoses","created":"2023-09-24","cited_by_count":10},{"id":"1609.02583","title":"Bottom-up Instance Segmentation using Deep Higher-Order CRFs","created":"2016-09-08","cited_by_count":8},{"id":"1810.04752","title":"Deep Recurrent Level Set for Segmenting Brain Tumors","created":"2018-10-10","cited_by_count":6},{"id":"2205.09299","title":"3DConvCaps: 3DUnet with Convolutional Capsule Encoder for Medical Image Segmentation","created":"2022-05-19","cited_by_count":3}],"next_cursor":null}