{"total":91,"rows":[{"id":"2407.08083","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","created":"2024-07-10","cited_by_count":224,"area":"ssm"},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"area":"ssm"},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141,"area":"ssm"},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102,"area":"ssm"},{"id":"2404.09498","title":"FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba","created":"2024-04-15","cited_by_count":81,"area":"ssm"},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2406.04207","title":"CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection","created":"2024-06-06","cited_by_count":48,"area":"ssm"},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2404.01705","title":"Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model","created":"2024-04-02","cited_by_count":37,"area":"ssm"},{"id":"2412.00678","title":"2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification","created":"2024-12-01","cited_by_count":35,"area":"ssm"},{"id":"2407.18559","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","created":"2024-07-26","cited_by_count":29,"area":"ssm"},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22,"area":"ssm"},{"id":"2405.17680","title":"Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports","created":"2024-05-27","cited_by_count":19,"area":"ssm"},{"id":"2410.03105","title":"Mamba in Vision: A Comprehensive Survey of Techniques and Applications","created":"2024-10-04","cited_by_count":18,"area":"ssm"},{"id":"2410.06806","title":"QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model","created":"2024-10-09","cited_by_count":18,"area":"ssm"},{"id":"2504.05794","title":"DefMamba: Deformable Visual State Space Model","created":"2025-04-08","cited_by_count":18,"area":"ssm"},{"id":"2411.15241","title":"EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality","created":"2024-11-22","cited_by_count":17,"area":"ssm"},{"id":"2410.02362","title":"A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyond","created":"2024-10-03","cited_by_count":16,"area":"ssm"},{"id":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2501.07810","title":"AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation","created":"2025-01-14","cited_by_count":16,"area":"ssm"},{"id":"2407.13772","title":"GroupMamba: Efficient Group-Based Visual State Space Model","created":"2024-07-18","cited_by_count":15,"area":"ssm"},{"id":"2411.17473","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","created":"2024-11-26","cited_by_count":15,"area":"ssm"},{"id":"2409.09649","title":"SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks","created":"2024-09-15","cited_by_count":14,"area":"ssm"},{"id":"2503.03437","title":"JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba","created":"2025-03-05","cited_by_count":14,"area":"ssm"},{"id":"2406.17815","title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","created":"2024-06-25","cited_by_count":12,"area":"ssm"},{"id":"2404.18213","title":"S$^2$Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification","created":"2024-04-28","cited_by_count":10,"area":"ssm"},{"id":"2405.18679","title":"Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain","created":"2024-05-29","cited_by_count":8,"area":"ssm"},{"id":"2409.09808","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","created":"2024-09-15","cited_by_count":8,"area":"ssm"},{"id":"2502.16907","title":"MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation","created":"2025-02-24","cited_by_count":8,"area":"ssm"},{"id":"2408.10575","title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval","created":"2024-08-20","cited_by_count":7,"area":"ssm"},{"id":"2411.16481","title":"Deformable Mamba for Wide Field of View Segmentation","created":"2024-11-25","cited_by_count":7,"area":"ssm"},{"id":"2410.10382","title":"V2M: Visual 2-Dimensional Mamba for Image Representation Learning","created":"2024-10-14","cited_by_count":6,"area":"ssm"},{"id":"2410.19894","title":"Topology-aware Mamba for Crack Segmentation in Structures","created":"2024-10-25","cited_by_count":6,"area":"ssm"},{"id":"2501.01262","title":"Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging","created":"2025-01-02","cited_by_count":6,"area":"ssm"},{"id":"2504.04787","title":"Dynamic Vision Mamba","created":"2025-04-07","cited_by_count":6,"area":"ssm"},{"id":"2412.12496","title":"Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training","created":"2024-12-17","cited_by_count":5,"area":"ssm"},{"id":"2511.06593","title":"Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion","created":"2025-11-10","cited_by_count":5,"area":"ssm"},{"id":"2501.16738","title":"Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization","created":"2025-01-28","cited_by_count":4,"area":"ssm"},{"id":"2603.16423","title":"SF-Mamba: Rethinking State Space Model for Vision","created":"2026-03-17","cited_by_count":4,"area":"ssm"},{"id":"2409.12108","title":"SPRMamba: Surgical Phase Recognition for Endoscopic Submucosal Dissection with Mamba","created":"2024-09-18","cited_by_count":3,"area":"ssm"},{"id":"2409.14403","title":"GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature Learning","created":"2024-09-22","cited_by_count":3,"area":"ssm"},{"id":"2412.16146","title":"Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks","created":"2024-12-20","cited_by_count":3,"area":"ssm"},{"id":"2410.23738","title":"MLLA-UNet: Mamba-like Linear Attention in an Efficient U-Shape Model for Medical Image Segmentation","created":"2024-10-31","cited_by_count":2,"area":"ssm"},{"id":"2412.07481","title":"Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence","created":"2024-12-10","cited_by_count":2,"area":"ssm"},{"id":"2502.11178","title":"DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection","created":"2025-02-16","cited_by_count":2,"area":"ssm"},{"id":"2503.01633","title":"SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning","created":"2025-03-03","cited_by_count":2,"area":"ssm"},{"id":"2504.01466","title":"Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes","created":"2025-04-02","cited_by_count":2,"area":"ssm"},{"id":"2505.12685","title":"Mamba-Adaptor: State Space Model Adaptor for Visual Recognition","created":"2025-05-19","cited_by_count":2,"area":"ssm"},{"id":"2507.19778","title":"HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning","created":"2025-07-26","cited_by_count":2,"area":"ssm"},{"id":"2508.02113","title":"DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal","created":"2025-08-04","cited_by_count":2,"area":"ssm"},{"id":"2509.16900","title":"ME-Mamba: Multi-Expert Mamba with Efficient Knowledge Capture and Fusion for Multimodal Survival Analysis","created":"2025-09-21","cited_by_count":2,"area":"ssm"},{"id":"2511.01315","title":"MVSMamba: Multi-View Stereo with State Space Model","created":"2025-11-03","cited_by_count":2,"area":"ssm"},{"id":"2406.16722","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","created":"2024-06-24","cited_by_count":1,"area":"ssm"},{"id":"2410.10316","title":"GlobalMamba: Global Image Serialization for Vision Mamba","created":"2024-10-14","cited_by_count":1,"area":"ssm"},{"id":"2503.06897","title":"Multi-granular body modeling with Redundancy-Free Spatiotemporal Fusion for Text-Driven Motion Generation","created":"2025-03-10","cited_by_count":1,"area":"ssm"},{"id":"2503.19427","title":"ASP-VMUNet: Atrous Shifted Parallel Vision Mamba U-Net for Skin Lesion Segmentation","created":"2025-03-25","cited_by_count":1,"area":"ssm"},{"id":"2505.14062","title":"FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry","created":"2025-05-20","cited_by_count":1,"area":"ssm"},{"id":"2506.15976","title":"LBMamba: Locally Bi-directional Mamba","created":"2025-06-19","cited_by_count":1,"area":"ssm"},{"id":"2507.14042","title":"Training-free Token Reduction for Vision Mamba","created":"2025-07-18","cited_by_count":1,"area":"ssm"},{"id":"2507.16624","title":"A2Mamba: Attention-augmented State Space Models for Visual Recognition","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2508.13712","title":"Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation","created":"2025-08-19","cited_by_count":1,"area":"ssm"},{"id":"2601.15929","title":"NeuroMamba: Multi-Perspective Feature Interaction with Visual Mamba for Neuron Segmentation","created":"2026-01-22","cited_by_count":1,"area":"ssm"},{"id":"2604.08038","title":"Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection","created":"2026-04-09","cited_by_count":1,"area":"ssm"},{"id":"2607.03589","title":"Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics","created":"2026-07-03","cited_by_count":1,"area":"ssm"},{"id":"2408.17081","title":"Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training","created":"2024-08-30","cited_by_count":0,"area":"ssm"},{"id":"2409.01093","title":"DS MYOLO: A Reliable Object Detector Based on SSMs for Driving Scenarios","created":"2024-09-02","cited_by_count":0,"area":"ssm"},{"id":"2411.09363","title":"When Mamba Meets xLSTM: An Efficient and Precise Method with the xLSTM-VMUNet Model for Skin lesion Segmentation","created":"2024-11-14","cited_by_count":0,"area":"ssm"},{"id":"2412.06211","title":"MSCrackMamba: Leveraging Vision Mamba for Crack Detection in Fused Multispectral Imagery","created":"2024-12-09","cited_by_count":0,"area":"ssm"},{"id":"2501.02040","title":"A Separable Self-attention Inspired by the State Space Model for Computer Vision","created":"2025-01-03","cited_by_count":0,"area":"ssm"},{"id":"2502.00594","title":"Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing","created":"2025-02-01","cited_by_count":0,"area":"ssm"},{"id":"2502.13524","title":"MobileViM: A Light-weight and Dimension-independent Vision Mamba for 3D Medical Image Analysis","created":"2025-02-19","cited_by_count":0,"area":"ssm"},{"id":"2505.20904","title":"HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion","created":"2025-05-27","cited_by_count":0,"area":"ssm"},{"id":"2506.01040","title":"ECP-Mamba: An Efficient Multi-scale Self-supervised Contrastive Learning Method with State Space Model for PolSAR Image Classification","created":"2025-06-01","cited_by_count":0,"area":"ssm"},{"id":"2506.08735","title":"InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba","created":"2025-06-10","cited_by_count":0,"area":"ssm"},{"id":"2507.18575","title":"HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation","created":"2025-07-24","cited_by_count":0,"area":"ssm"},{"id":"2507.23371","title":"VMatcher: State-Space Semi-Dense Local Feature Matching","created":"2025-07-31","cited_by_count":0,"area":"ssm"},{"id":"2508.01591","title":"Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection","created":"2025-08-03","cited_by_count":0,"area":"ssm"},{"id":"2508.07363","title":"Keyword Mamba: Spoken Keyword Spotting with State Space Models","created":"2025-08-10","cited_by_count":0,"area":"ssm"},{"id":"2509.22691","title":"Sequential Token Merging: Revisiting Hidden States","created":"2025-09-19","cited_by_count":0,"area":"ssm"},{"id":"2510.21079","title":"WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition","created":"2025-10-24","cited_by_count":0,"area":"ssm"},{"id":"2512.00647","title":"MambaScope: Coarse-to-Fine Scoping for Efficient Vision Mamba","created":"2025-11-29","cited_by_count":0,"area":"ssm"},{"id":"2512.02727","title":"DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions","created":"2025-12-02","cited_by_count":0,"area":"ssm"},{"id":"2603.03806","title":"Separators in Enhancing Autoregressive Pretraining for Vision Mamba","created":"2026-03-04","cited_by_count":0,"area":"ssm"},{"id":"2603.18031","title":"InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model","created":"2026-03-08","cited_by_count":0,"area":"ssm"},{"id":"2603.20074","title":"MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models","created":"2026-03-20","cited_by_count":0,"area":"ssm"},{"id":"2604.13426","title":"Event-Adaptive State Transition and Gated Fusion for RGB-Event Object Tracking","created":"2026-04-15","cited_by_count":0,"area":"ssm"},{"id":"2605.11300","title":"Can Graphs Help Vision SSMs See Better?","created":"2026-05-11","cited_by_count":0,"area":"ssm"},{"id":"2607.18625","title":"Norm or Direction? Decoding Vision Mambas for High-Resolution Vision","created":"2026-07-21","cited_by_count":0,"area":"ssm"},{"id":"2609.24337","title":"LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba","created":"2026-09-21","cited_by_count":0,"area":"ssm"}],"next_cursor":null}