{"list":"other","total":58,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"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":"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":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"1911.07559","title":"FFA-Net: Feature Fusion Attention Network for Single Image Dehazing","created":"2019-11-18","cited_by_count":307},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"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":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1506.04579","title":"ParseNet: Looking Wider to See Better","created":"2015-06-15","cited_by_count":177},{"id":"2003.04092","title":"Searching Central Difference Convolutional Networks for Face Anti-Spoofing","created":"2020-03-09","cited_by_count":173},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136},{"id":"1407.5736","title":"Learning Rich Features from RGB-D Images for Object Detection and Segmentation","created":"2014-07-22","cited_by_count":127},{"id":"2007.09183","title":"Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation","created":"2020-07-17","cited_by_count":122},{"id":"1905.10089","title":"ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation","created":"2019-05-24","cited_by_count":107},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89},{"id":"2011.06961","title":"Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis","created":"2020-11-13","cited_by_count":84},{"id":"2108.10528","title":"ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation","created":"2021-08-24","cited_by_count":77},{"id":"1803.06791","title":"Depth-aware CNN for RGB-D Segmentation","created":"2018-03-19","cited_by_count":74},{"id":"1504.01013","title":"Efficient piecewise training of deep structured models for semantic segmentation","created":"2015-04-04","cited_by_count":71},{"id":"2008.12134","title":"Siamese Network for RGB-D Salient Object Detection and Beyond","created":"2020-08-26","cited_by_count":67},{"id":"1806.01054","title":"RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation","created":"2018-06-04","cited_by_count":66},{"id":"2104.02745","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","created":"2021-04-06","cited_by_count":65},{"id":"2004.04534","title":"Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation","created":"2020-04-09","cited_by_count":48},{"id":"2111.14382","title":"VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion","created":"2021-11-29","cited_by_count":48},{"id":"2203.10739","title":"Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation","created":"2022-03-21","cited_by_count":47},{"id":"1612.02844","title":"Deep TEN: Texture Encoding Network","created":"2016-12-08","cited_by_count":44},{"id":"2102.02996","title":"Deep Texture-Aware Features for Camouflaged Object Detection","created":"2021-02-05","cited_by_count":36},{"id":"2007.09365","title":"Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing","created":"2020-07-18","cited_by_count":24},{"id":"2101.12482","title":"Self-Supervised Pretraining for RGB-D Salient Object Detection","created":"2021-01-29","cited_by_count":20},{"id":"2109.00699","title":"FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation","created":"2021-09-02","cited_by_count":17},{"id":"1912.11691","title":"Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images","created":"2019-12-25","cited_by_count":13},{"id":"2201.01427","title":"Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation","created":"2022-01-05","cited_by_count":6},{"id":"2206.03939","title":"Depth-Adapted CNNs for RGB-D Semantic Segmentation","created":"2022-06-08","cited_by_count":6}],"next_cursor":null}