{"total":128,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091,"area":null},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855,"area":null},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532,"area":null},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288,"area":null},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101,"area":null},{"id":"2107.12292","title":"Contextual Transformer Networks for Visual Recognition","created":"2021-07-26","cited_by_count":90,"area":null},{"id":"2105.04206","title":"You Only Learn One Representation: Unified Network for Multiple Tasks","created":"2021-05-10","cited_by_count":86,"area":null},{"id":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72,"area":null},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71,"area":null},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"area":null},{"id":"2204.07683","title":"Safe Self-Refinement for Transformer-based Domain Adaptation","created":"2022-04-16","cited_by_count":61,"area":null},{"id":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52,"area":null},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50,"area":null},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48,"area":null},{"id":"2108.11819","title":"Mining Contextual Information Beyond Image for Semantic Segmentation","created":"2021-08-26","cited_by_count":48,"area":null},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46,"area":null},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46,"area":null},{"id":"2104.09805","title":"CTNet: Context-based Tandem Network for Semantic Segmentation","created":"2021-04-20","cited_by_count":43,"area":null},{"id":"2204.02557","title":"MixFormer: Mixing Features across Windows and Dimensions","created":"2022-04-06","cited_by_count":43,"area":null},{"id":"2102.02696","title":"Active Boundary Loss for Semantic Segmentation","created":"2021-02-04","cited_by_count":40,"area":null},{"id":"2108.12382","title":"ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation","created":"2021-08-27","cited_by_count":40,"area":null},{"id":"2108.06383","title":"DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange","created":"2021-08-13","cited_by_count":36,"area":null},{"id":"2203.10790","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","created":"2022-03-21","cited_by_count":36,"area":null},{"id":"2101.06175","title":"PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation","created":"2021-01-15","cited_by_count":35,"area":null},{"id":"2110.11062","title":"Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation","created":"2021-10-21","cited_by_count":34,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2211.04800","title":"Designing Network Design Strategies Through Gradient Path Analysis","created":"2022-11-09","cited_by_count":32,"area":null},{"id":"2107.03172","title":"Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World","created":"2021-07-07","cited_by_count":30,"area":null},{"id":"2201.01615","title":"Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention","created":"2022-01-05","cited_by_count":30,"area":null},{"id":"2203.12612","title":"StructToken : Rethinking Semantic Segmentation with Structural Prior","created":"2022-03-23","cited_by_count":30,"area":null},{"id":"2102.12152","title":"Dual-Awareness Attention for Few-Shot Object Detection","created":"2021-02-24","cited_by_count":29,"area":null},{"id":"2108.12468","title":"Learning Inner-Group Relations on Point Clouds","created":"2021-08-27","cited_by_count":29,"area":null},{"id":"2207.06580","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","created":"2022-07-14","cited_by_count":29,"area":null},{"id":"2101.08085","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28,"area":null},{"id":"2112.05006","title":"Exploring Event-driven Dynamic Context for Accident Scene Segmentation","created":"2021-12-09","cited_by_count":23,"area":null},{"id":"2108.09174","title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","created":"2021-08-20","cited_by_count":22,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2211.01644","title":"StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2409.20398","title":"AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2101.07034","title":"AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing","created":"2021-01-18","cited_by_count":16,"area":null},{"id":"2203.14679","title":"Brain-inspired Multilayer Perceptron with Spiking Neurons","created":"2022-03-28","cited_by_count":16,"area":null},{"id":"2107.14209","title":"A Unified Efficient Pyramid Transformer for Semantic Segmentation","created":"2021-07-29","cited_by_count":14,"area":null},{"id":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2105.13033","title":"SSAN: Separable Self-Attention Network for Video Representation Learning","created":"2021-05-27","cited_by_count":13,"area":null},{"id":"2107.04735","title":"Local-to-Global Self-Attention in Vision Transformers","created":"2021-07-10","cited_by_count":13,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2303.13896","title":"Regularization of polynomial networks for image recognition","created":"2023-03-24","cited_by_count":13,"area":null},{"id":"2106.15338","title":"Probabilistic Attention for Interactive Segmentation","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2111.10790","title":"DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction","created":"2021-11-21","cited_by_count":12,"area":null},{"id":"2204.10760","title":"iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition","created":"2022-04-22","cited_by_count":12,"area":null},{"id":"2207.14452","title":"Deep Learning-based Occluded Person Re-identification: A Survey","created":"2022-07-29","cited_by_count":12,"area":null},{"id":"2401.17992","title":"Multilinear Operator Networks","created":"2024-01-31","cited_by_count":12,"area":null},{"id":"2112.04108","title":"Fully Attentional Network for Semantic Segmentation","created":"2021-12-08","cited_by_count":11,"area":null},{"id":"2212.07911","title":"Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation","created":"2022-12-15","cited_by_count":11,"area":null},{"id":"2402.00407","title":"InfMAE: A Foundation Model in the Infrared Modality","created":"2024-02-01","cited_by_count":11,"area":null},{"id":"2111.11567","title":"ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images","created":"2021-11-22","cited_by_count":10,"area":null},{"id":"2111.13923","title":"Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution","created":"2021-11-27","cited_by_count":10,"area":null},{"id":"2209.04471","title":"MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation","created":"2022-09-09","cited_by_count":10,"area":null},{"id":"2211.15595","title":"FsaNet: Frequency Self-attention for Semantic Segmentation","created":"2022-11-28","cited_by_count":10,"area":null},{"id":"2305.12231","title":"Bi-VLGM : Bi-Level Class-Severity-Aware Vision-Language Graph Matching for Text Guided Medical Image Segmentation","created":"2023-05-20","cited_by_count":10,"area":null},{"id":"2307.02092","title":"Make A Long Image Short: Adaptive Token Length for Vision Transformers","created":"2023-07-05","cited_by_count":10,"area":null},{"id":"2212.07623","title":"SBSS: Stacking-Based Semantic Segmentation Framework for Very High Resolution Remote Sensing Image","created":"2022-12-15","cited_by_count":9,"area":null},{"id":"2207.11396","title":"Orientation and Context Entangled Network for Retinal Vessel Segmentation","created":"2022-07-23","cited_by_count":8,"area":null},{"id":"2306.14810","title":"Robust Wind Turbine Blade Segmentation from RGB Images in the Wild","created":"2023-06-26","cited_by_count":8,"area":null},{"id":"2309.04422","title":"Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving","created":"2023-09-08","cited_by_count":8,"area":null},{"id":"2108.01866","title":"Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation","created":"2021-08-04","cited_by_count":7,"area":null},{"id":"2112.07106","title":"E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation","created":"2021-12-14","cited_by_count":7,"area":null},{"id":"2308.01944","title":"Dynamic Token-Pass Transformers for Semantic Segmentation","created":"2023-08-03","cited_by_count":7,"area":null},{"id":"2310.10755","title":"IDRNet: Intervention-Driven Relation Network for Semantic Segmentation","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2203.10395","title":"Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning","created":"2022-03-19","cited_by_count":6,"area":null},{"id":"2308.07592","title":"Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation","created":"2023-08-15","cited_by_count":6,"area":null},{"id":"2110.14587","title":"Boundary Guided Context Aggregation for Semantic Segmentation","created":"2021-10-27","cited_by_count":5,"area":null},{"id":"2212.07890","title":"Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2303.08029","title":"Class-level Multiple Distributions Representation are Necessary for Semantic Segmentation","created":"2023-03-14","cited_by_count":5,"area":null},{"id":"2111.00770","title":"Dense Prediction with Attentive Feature Aggregation","created":"2021-11-01","cited_by_count":4,"area":null},{"id":"2111.13677","title":"SWAT: Spatial Structure Within and Among Tokens","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2203.00138","title":"Spatiotemporal Transformer Attention Network for 3D Voxel Level Joint Segmentation and Motion Prediction in Point Cloud","created":"2022-02-28","cited_by_count":4,"area":null},{"id":"2203.00172","title":"Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention","created":"2022-03-01","cited_by_count":4,"area":null},{"id":"2212.13764","title":"Representation Separation for Semantic Segmentation with Vision Transformers","created":"2022-12-28","cited_by_count":4,"area":null},{"id":"2304.08842","title":"UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite","created":"2023-04-18","cited_by_count":4,"area":null},{"id":"2305.17091","title":"SSSegmenation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2408.15388","title":"Panoptic Perception for Autonomous Driving: A Survey","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2412.03297","title":"Composed Image Retrieval for Training-Free Domain Conversion","created":"2024-12-04","cited_by_count":4,"area":null},{"id":"2412.20838","title":"Dual-Space Augmented Intrinsic-LoRA for Wind Turbine Segmentation","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2108.02451","title":"Unifying Nonlocal Blocks for Neural Networks","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2109.02580","title":"Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2201.09139","title":"Dual-Flattening Transformers through Decomposed Row and Column Queries for Semantic Segmentation","created":"2022-01-22","cited_by_count":3,"area":null},{"id":"2403.01156","title":"Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation","created":"2024-03-02","cited_by_count":3,"area":null},{"id":"2412.08671","title":"A Deep Semantic Segmentation Network with Semantic and Contextual Refinements","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2503.12453","title":"Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2111.00193","title":"M2MRF: Many-to-Many Reassembly of Features for Tiny Lesion Segmentation in Fundus Images","created":"2021-10-30","cited_by_count":2,"area":null},{"id":"2211.12455","title":"ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation","created":"2022-11-22","cited_by_count":2,"area":null}],"next_cursor":"100"}