{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2211.14461","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","created":"2022-11-26","cited_by_count":223},{"id":"1812.01593","title":"Improving Semantic Segmentation via Video Propagation and Label Relaxation","created":"2018-12-04","cited_by_count":134},{"id":"2308.02097","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","created":"2023-08-04","cited_by_count":129},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"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":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"1807.11699","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","created":"2018-07-31","cited_by_count":88},{"id":"1804.02176","title":"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks","created":"2018-04-06","cited_by_count":84},{"id":"2003.09210","title":"DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion","created":"2020-03-20","cited_by_count":73},{"id":"2008.11351","title":"SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection","created":"2020-08-26","cited_by_count":66},{"id":"2209.15001","title":"Dilated Neighborhood Attention Transformer","created":"2022-09-29","cited_by_count":64},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64},{"id":"2309.09668","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","created":"2023-09-18","cited_by_count":60},{"id":"1908.00894","title":"Pothole Detection Based on Disparity Transformation and Road Surface Modeling","created":"2019-08-02","cited_by_count":38},{"id":"2206.09907","title":"ORFD: A Dataset and Benchmark for Off-Road Freespace Detection","created":"2022-06-20","cited_by_count":33},{"id":"2303.17386","title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","created":"2023-03-30","cited_by_count":27},{"id":"2309.10356","title":"RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing","created":"2023-09-19","cited_by_count":27},{"id":"1910.04988","title":"Road Damage Detection Based on Unsupervised Disparity Map Segmentation","created":"2019-10-11","cited_by_count":24},{"id":"2011.13313","title":"Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion","created":"2020-11-26","cited_by_count":24},{"id":"2107.14599","title":"SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection","created":"2021-07-30","cited_by_count":23},{"id":"2404.06261","title":"Playing to Vision Foundation Model's Strengths in Stereo Matching","created":"2024-04-09","cited_by_count":23},{"id":"2401.01624","title":"Context-Aware Interaction Network for RGB-T Semantic Segmentation","created":"2024-01-03","cited_by_count":21},{"id":"2008.11383","title":"Applying Surface Normal Information in Drivable Area and Road Anomaly Detection for Ground Mobile Robots","created":"2020-08-26","cited_by_count":20},{"id":"2203.10856","title":"RGB-Depth Fusion GAN for Indoor Depth Completion","created":"2022-03-21","cited_by_count":18},{"id":"2401.11414","title":"S$^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving","created":"2024-01-21","cited_by_count":15},{"id":"2108.11224","title":"Multi-domain semantic segmentation with overlapping labels","created":"2021-08-25","cited_by_count":14},{"id":"2309.04001","title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","created":"2023-09-07","cited_by_count":12},{"id":"2304.12031","title":"D2NT: A High-Performing Depth-to-Normal Translator","created":"2023-04-24","cited_by_count":10},{"id":"2404.03527","title":"HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion","created":"2024-04-04","cited_by_count":10},{"id":"2402.18918","title":"SNE-RoadSegV2: Advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection","created":"2024-02-29","cited_by_count":8},{"id":"2312.03430","title":"ShareCMP: Polarization-Aware RGB-P Semantic Segmentation","created":"2023-12-06","cited_by_count":7},{"id":"2107.13279","title":"Pseudo-LiDAR Based Road Detection","created":"2021-07-28","cited_by_count":6}],"next_cursor":null}