{"total":81,"rows":[{"id":"2411.15269","title":"MambaIRv2: Attentive State Space Restoration","created":"2024-11-22","cited_by_count":94,"area":"ssm"},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2404.18861","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":"2502.19854","title":"One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion","created":"2025-02-27","cited_by_count":32,"area":null},{"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":"2412.18076","title":"COMO: Cross-Mamba Interaction and Offset-Guided Fusion for Multimodal Object Detection","created":"2024-12-24","cited_by_count":18,"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":"2411.06481","title":"KMM: Key Frame Mask Mamba for Extended Motion Generation","created":"2024-11-10","cited_by_count":16,"area":"ssm"},{"id":"2503.01113","title":"SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures","created":"2025-03-03","cited_by_count":16,"area":"ssm"},{"id":"2503.24065","title":"COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation","created":"2025-03-31","cited_by_count":15,"area":"ssm"},{"id":"2502.14471","title":"Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well","created":"2025-02-20","cited_by_count":14,"area":null},{"id":"2504.14582","title":"NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results","created":"2025-04-20","cited_by_count":12,"area":null},{"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":"2503.18970","title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba","created":"2025-03-22","cited_by_count":9,"area":"ssm"},{"id":"2502.13624","title":"CardiacMamba: A Multimodal RGB-RF Fusion Framework with State Space Models for Remote Physiological Measurement","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2503.13214","title":"A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpening","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2505.03401","title":"DDaTR: Dynamic Difference-aware Temporal Residual Network for Longitudinal Radiology Report Generation","created":"2025-05-06","cited_by_count":8,"area":null},{"id":"2505.16811","title":"Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2406.15910","title":"Soft Masked Mamba Diffusion Model for CT to MRI Conversion","created":"2024-06-22","cited_by_count":7,"area":"diffusion"},{"id":"2409.07040","title":"Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement","created":"2024-09-11","cited_by_count":6,"area":null},{"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":"2508.02192","title":"Content-Aware Mamba for Learned Image Compression","created":"2025-08-04","cited_by_count":6,"area":"ssm"},{"id":"2502.02163","title":"Progressive Correspondence Regenerator for Robust 3D Registration","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2503.15934","title":"SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer","created":"2025-03-20","cited_by_count":5,"area":"ssm"},{"id":"2503.23450","title":"AU-TTT: Vision Test-Time Training model for Facial Action Unit Detection","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2505.06796","title":"Multimodal Fake News Detection: MFND Dataset and Shallow-Deep Multitask Learning","created":"2025-05-11","cited_by_count":5,"area":null},{"id":"2511.06593","title":"Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion","created":"2025-11-10","cited_by_count":5,"area":"ssm"},{"id":"2503.00429","title":"DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2503.12912","title":"Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2503.21124","title":"AdaMHF: Adaptive Multimodal Hierarchical Fusion for Survival Prediction","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2507.01384","title":"MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing","created":"2025-07-02","cited_by_count":3,"area":"ssm"},{"id":"2508.11849","title":"LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mamba","created":"2025-08-16","cited_by_count":3,"area":"ssm"},{"id":"2510.10160","title":"SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation","created":"2025-10-11","cited_by_count":3,"area":"ssm"},{"id":"2603.13340","title":"Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2406.10933","title":"Improving Adversarial Robustness via Decoupled Visual Representation Masking","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2503.06446","title":"M$^3$amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification","created":"2025-03-09","cited_by_count":2,"area":"ssm"},{"id":"2503.18378","title":"Exploring State Space Model in Wavelet Domain: An Infrared and Visible Image Fusion Network via Wavelet Transform and State Space Model","created":"2025-03-24","cited_by_count":2,"area":"ssm"},{"id":"2505.14715","title":"A Comprehensive Review of Techniques, Algorithms, Advancements, Challenges, and Clinical Applications of Multi-modal Medical Image Fusion for Improved Diagnosis","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2506.15218","title":"DM-FNet: Unified multimodal medical image fusion via diffusion process-trained encoder-decoder","created":"2025-06-18","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":"2506.23783","title":"Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking","created":"2025-06-30","cited_by_count":2,"area":"ssm"},{"id":"2510.16036","title":"IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection","created":"2025-10-16","cited_by_count":2,"area":"mllm"},{"id":"2512.20921","title":"Self-supervised Multiplex Consensus Mamba for General Image Fusion","created":"2025-12-24","cited_by_count":2,"area":"ssm"},{"id":"2604.02896","title":"EvaNet: Towards More Efficient and Consistent Infrared and Visible Image Fusion Assessment","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2504.10871","title":"DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2504.20362","title":"TTTFusion: A Test-Time Training-Based Strategy for Multimodal Medical Image Fusion in Surgical Robots","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2506.03555","title":"WIFE-Fusion:Wavelet-aware Intra-inter Frequency Enhancement for Multi-model Image Fusion","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2506.22736","title":"UniFuse: A Unified All-in-One Framework for Multi-Modal Medical Image Fusion Under Diverse Degradations and Misalignments","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2508.03008","title":"ClinicalFMamba: Advancing Clinical Assessment using Mamba-based Multimodal Neuroimaging Fusion","created":"2025-08-05","cited_by_count":1,"area":"ssm"},{"id":"2510.11456","title":"Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusion","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2511.02349","title":"M3PD Dataset: Dual-view Photoplethysmography (PPG) Using Front-and-rear Cameras of Smartphones in Lab and Clinical Settings","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.12432","title":"Text-Guided Channel Perturbation and Pretrained Knowledge Integration for Unified Multi-Modality Image Fusion","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2512.12586","title":"StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2604.10695","title":"Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2605.11840","title":"Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation","created":"2026-05-12","cited_by_count":1,"area":"ssm"},{"id":"2408.10883","title":"Dynamic Analysis and Adaptive Discriminator for Fake News Detection","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2409.10328","title":"Fuse4Seg: Image Fusion for Multi-Modal Medical Segmentation via Bi-level Optimization","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2411.10036","title":"Rethinking Normalization Strategies and Convolutional Kernels for Multimodal Image Fusion","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2503.13073","title":"DehazeMamba: SAR-guided Optical Remote Sensing Image Dehazing with Adaptive State Space Model","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2506.12747","title":"Unleashing Diffusion and State Space Models for Medical Image Segmentation","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2508.05476","title":"MM2CT: MR-to-CT translation for multi-modal image fusion with mamba","created":"2025-08-07","cited_by_count":0,"area":"ssm"},{"id":"2508.17397","title":"Enhancing Underwater Images via Deep Learning: A Comparative Study of VGG19 and ResNet50-Based Approaches","created":"2025-08-24","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":"2509.06282","title":"AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.07593","title":"Vision-Proprioception Fusion with Mamba2 in End-to-End Reinforcement Learning for Motion Control","created":"2025-09-09","cited_by_count":0,"area":"ssm"},{"id":"2510.04628","title":"A Spatial-Spectral-Frequency Interactive Network for Multimodal Remote Sensing Classification","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2512.15211","title":"WLC: Weber-Inspired Local Contrast Metric for Low-Altitude Image Fusion","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2512.15971","title":"From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.05538","title":"DIFF-MF: A Difference-Driven Channel-Spatial State Space Model for Multi-Modal Image Fusion","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2601.16631","title":"PanopMamba: Vision State Space Modeling for Nuclei Panoptic Segmentation","created":"2026-01-23","cited_by_count":0,"area":"ssm"},{"id":"2601.17288","title":"Fluxamba: Topology-Aware Anisotropic State Space Models for Geological Lineament Segmentation in Multi-Source Remote Sensing","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2601.20260","title":"Reversible Efficient Diffusion for Image Fusion","created":"2026-01-28","cited_by_count":0,"area":"diffusion"},{"id":"2602.04405","title":"Interactive Spatial-Frequency Fusion Mamba for Multi-Modal Image Fusion","created":"2026-02-04","cited_by_count":0,"area":"ssm"},{"id":"2603.07120","title":"Inter-Image Pixel Shuffling for Multi-focus Image Fusion","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.21820","title":"Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.24296","title":"AMIF: Authorizable Medical Image Fusion Model with Built-in Authentication","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.05748","title":"SVC 2026: the Second Multimodal Deception Detection Challenge and the First Domain Generalized Remote Physiological Measurement Challenge","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.08922","title":"Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.12463","title":"Euler-inspired Decoupling Neural Operator for Efficient Pansharpening","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2608.07848","title":"IRPol-Fuse: Energy-structure coordination for infrared polarization fusion under low visibility","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}