{"total":71,"rows":[{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2412.15691","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","created":"2024-12-20","cited_by_count":57,"area":null},{"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":"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":"2409.19613","title":"Hybrid Mamba for Few-Shot Segmentation","created":"2024-09-29","cited_by_count":21,"area":"ssm"},{"id":"2412.10707","title":"MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt","created":"2024-12-14","cited_by_count":20,"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":"2408.11758","title":"MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs","created":"2024-08-21","cited_by_count":14,"area":"ssm"},{"id":"2407.06839","title":"A Mamba-based Siamese Network for Remote Sensing Change Detection","created":"2024-07-08","cited_by_count":13,"area":"ssm"},{"id":"2408.10854","title":"MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling","created":"2024-08-20","cited_by_count":12,"area":"ssm"},{"id":"2410.19872","title":"Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2412.20084","title":"STNMamba: Mamba-based Spatial-Temporal Normality Learning for Video Anomaly Detection","created":"2024-12-28","cited_by_count":9,"area":"ssm"},{"id":"2409.13912","title":"OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping","created":"2024-09-20","cited_by_count":8,"area":null},{"id":"2410.13532","title":"RemoteDet-Mamba: A Hybrid Mamba-CNN Network for Multi-modal Object Detection in Remote Sensing Images","created":"2024-10-17","cited_by_count":7,"area":"ssm"},{"id":"2504.02801","title":"F-ViTA: Foundation Model Guided Visible to Thermal Translation","created":"2025-04-03","cited_by_count":7,"area":"diffusion"},{"id":"2508.00421","title":"UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken","created":"2025-08-01","cited_by_count":7,"area":"ssm"},{"id":"2503.02619","title":"XFMamba: Cross-Fusion Mamba for Multi-View Medical Image Classification","created":"2025-03-04","cited_by_count":6,"area":"ssm"},{"id":"2507.14643","title":"Multispectral State-Space Feature Fusion: Bridging Shared and Cross-Parametric Interactions for Object Detection","created":"2025-07-19","cited_by_count":6,"area":null},{"id":"2512.11719","title":"Referring Change Detection in Remote Sensing Imagery","created":"2025-12-12","cited_by_count":6,"area":null},{"id":"2509.19873","title":"SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding","created":"2025-09-24","cited_by_count":5,"area":"inference"},{"id":"2511.06593","title":"Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion","created":"2025-11-10","cited_by_count":5,"area":"ssm"},{"id":"2505.24361","title":"Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation","created":"2025-05-30","cited_by_count":4,"area":"distill"},{"id":"2506.23283","title":"MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition","created":"2025-06-29","cited_by_count":4,"area":"ssm"},{"id":"2408.10679","title":"Alignment-free Raw Video Demoireing","created":"2024-08-20","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":"2411.17532","title":"FTMoMamba: Motion Generation with Frequency and Text State Space Models","created":"2024-11-26","cited_by_count":3,"area":"diffusion"},{"id":"2503.17261","title":"Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images","created":"2025-03-21","cited_by_count":3,"area":"ssm"},{"id":"2507.05948","title":"Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2507.22477","title":"LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks","created":"2025-07-30","cited_by_count":3,"area":"ssm"},{"id":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3,"area":"ssm"},{"id":"2510.27508","title":"Context-Gated Cross-Modal Perception with Visual Mamba for PET-CT Lung Tumor Segmentation","created":"2025-10-31","cited_by_count":3,"area":"ssm"},{"id":"2602.18717","title":"NeXt2Former-CD: Efficient Remote Sensing Change Detection with Modern Vision Architectures","created":"2026-02-21","cited_by_count":3,"area":null},{"id":"2505.15491","title":"Spectral-Aware Global Fusion for RGB-Thermal Semantic Segmentation","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.17869","title":"Cross-modal State Space Modeling for Real-time RGB-thermal Wild Scene Semantic Segmentation","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2508.03060","title":"CHARM: Collaborative Harmonization across Arbitrary Modalities for Modality-agnostic Semantic Segmentation","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2509.10005","title":"TUNI: Unifying Pre-training and Fine-tuning with Modality-Aware Mutual Learning and Rectification for RGB-T Semantic Segmentation","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2509.18683","title":"LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object Detection","created":"2025-09-23","cited_by_count":2,"area":"ssm"},{"id":"2511.13047","title":"DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2407.02109","title":"HRSAM: Efficient Interactive Segmentation in High-Resolution Images","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2503.04199","title":"MASTER: Multimodal Segmentation with Text Prompts","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2506.08629","title":"ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Network","created":"2025-06-10","cited_by_count":1,"area":"ssm"},{"id":"2508.07797","title":"Power Battery Detection","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2509.03872","title":"Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2511.19882","title":"ChessMamba: Structure-Aware Interleaving of State Spaces for Change Detection in Remote Sensing Images","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.08293","title":"M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction","created":"2026-01-13","cited_by_count":1,"area":"ssm"},{"id":"2604.11585","title":"GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.12319","title":"RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2608.27971","title":"GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2411.00233","title":"SambaMixer: State of Health Prediction of Li-ion Batteries using Mamba State Space Models","created":"2024-10-31","cited_by_count":0,"area":"ssm"},{"id":"2412.19650","title":"Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP","created":"2024-12-27","cited_by_count":0,"area":null},{"id":"2503.00747","title":"LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2505.12007","title":"Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression Recognition","created":"2025-05-17","cited_by_count":0,"area":"moe"},{"id":"2505.20041","title":"DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2508.21135","title":"HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection","created":"2025-08-28","cited_by_count":0,"area":"ssm"},{"id":"2511.06716","title":"MirrorMamba: Towards Scalable and Robust Mirror Detection in Videos","created":"2025-11-10","cited_by_count":0,"area":"ssm"},{"id":"2601.14776","title":"M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.19832","title":"M3S-Net: Multimodal Feature Fusion Network Based on Multi-scale Data for Ultra-short-term PV Power Forecasting","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2602.23559","title":"No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.18462","title":"AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba","created":"2026-03-19","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":"2604.05527","title":"Prior-guided Fusion of Multimodal Features for Change Detection from Optical-SAR Images","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.17585","title":"DGSSM: Diffusion guided state-space models for multimodal salient object detection","created":"2026-04-19","cited_by_count":0,"area":"ssm"},{"id":"2605.14626","title":"UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.26273","title":"Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.26849","title":"Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.20326","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.23451","title":"Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.03559","title":"Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05671","title":"URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":null}