{"total":47,"rows":[{"id":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","cited_by_count":62,"area":null},{"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":"2405.16105","title":"MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2408.03703","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","created":"2024-08-07","cited_by_count":12,"area":null},{"id":"2405.14480","title":"Scalable Visual State Space Model with Fractal Scanning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2511.01243","title":"CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation","created":"2025-11-03","cited_by_count":8,"area":null},{"id":"2602.21917","title":"Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration","created":"2026-02-25","cited_by_count":8,"area":null},{"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":"2504.19198","title":"Adaptive Dual-domain Learning for Underwater Image Enhancement","created":"2025-04-27","cited_by_count":6,"area":null},{"id":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2409.16592","title":"MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2603.02629","title":"Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective","created":"2026-03-03","cited_by_count":4,"area":null},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2602.01194","title":"EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2604.14724","title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2412.11214","title":"Image Forgery Localization with State Space Models","created":"2024-12-15","cited_by_count":2,"area":null},{"id":"2503.16910","title":"Salient Object Detection in Traffic Scene through the TSOD10K Dataset","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2506.21137","title":"Norm$\\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2410.24075","title":"Identifying Spatio-Temporal Drivers of Extreme Events","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.17283","title":"BadScan: An Architectural Backdoor Attack on Visual State Space Models","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2509.25570","title":"AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2601.11164","title":"SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.04170","title":"Partial Ring Scan: Revisiting Scan Order in Vision State Space Models","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2412.19646","title":"Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection","created":"2024-12-27","cited_by_count":0,"area":null},{"id":"2503.02270","title":"SSNet: Saliency Prior and State Space Model-based Network for Salient Object Detection in RGB-D Images","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2503.21262","title":"vGamba: Attentive State Space Bottleneck for efficient Long-range Dependencies in Visual Recognition","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2510.06564","title":"HSNet: Heterogeneous Subgraph Network for Single Image Super-resolution","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2511.19963","title":"MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.06419","title":"Learning Human Visual Attention on 3D Surfaces through Geometry-Queried Semantic Priors","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.15967","title":"Non-Contact Physiological Monitoring in Pediatric Intensive Care Units via Adaptive Masking and Self-Supervised Learning","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.16915","title":"StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.04882","title":"DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.16243","title":"RASLF: Representation-Aware State Space Model for Light Field Super-Resolution","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.23977","title":"Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE Solving and Visual Perception","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2605.11563","title":"TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.16404","title":"Hybrid Quantum-MambaVision: A Quantum-enhanced State Space Model for Calibrated Mixed-type Wafer Defect Detection","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.27843","title":"VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection","created":"2026-07-30","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":"2608.23746","title":"CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Semantic Segmentation","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25568","title":"CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.11081","title":"TailProp: content-adaptive light- and heavy-tailed propagation for vision","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.33325","title":"VisionHOPE: Visual Backbones as Self-Modifying Learning Systems","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}