{"total":400,"rows":[{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2406.02918","title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation","created":"2024-06-05","cited_by_count":179,"area":null},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98,"area":null},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92,"area":null},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90,"area":null},{"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":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51,"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":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2404.09790","title":"NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Results","created":"2024-04-15","cited_by_count":40,"area":null},{"id":"2406.04875","title":"3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views","created":"2024-06-07","cited_by_count":39,"area":null},{"id":"2407.11087","title":"Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV","created":"2024-07-14","cited_by_count":36,"area":null},{"id":"2410.00379","title":"CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2501.15061","title":"PolaFormer: Polarity-aware Linear Attention for Vision Transformers","created":"2025-01-25","cited_by_count":32,"area":null},{"id":"2412.11890","title":"SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation","created":"2024-12-16","cited_by_count":31,"area":null},{"id":"2405.14343","title":"Efficient Visual State Space Model for Image Deblurring","created":"2024-05-23","cited_by_count":29,"area":null},{"id":"2501.18783","title":"RUN: Reversible Unfolding Network for Concealed Object Segmentation","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2502.03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2404.14248","title":"NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results","created":"2024-04-22","cited_by_count":26,"area":null},{"id":"2405.15731","title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","created":"2024-05-24","cited_by_count":26,"area":null},{"id":"2402.03496","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","created":"2024-02-05","cited_by_count":25,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2405.03673","title":"MemoryMamba: Memory-Augmented State Space Model for Defect Recognition","created":"2024-05-06","cited_by_count":24,"area":null},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23,"area":null},{"id":"2407.02315","title":"VFIMamba: Video Frame Interpolation with State Space Models","created":"2024-07-02","cited_by_count":22,"area":null},{"id":"2505.06683","title":"UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration","created":"2025-05-10","cited_by_count":22,"area":null},{"id":"2405.15214","title":"PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2503.12461","title":"MambaIC: State Space Models for High-Performance Learned Image Compression","created":"2025-03-16","cited_by_count":20,"area":null},{"id":"2406.10322","title":"LieRE: Lie Rotational Positional Encodings","created":"2024-06-14","cited_by_count":18,"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":"2505.23525","title":"Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization","created":"2025-05-29","cited_by_count":16,"area":null},{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2403.16520","title":"CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification","created":"2024-03-25","cited_by_count":15,"area":null},{"id":"2503.20824","title":"Exploiting Temporal State Space Sharing for Video Semantic Segmentation","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2506.02475","title":"Comba: Improving Bilinear RNNs with Closed-loop Control","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2410.17241","title":"Frontiers in Intelligent Colonoscopy","created":"2024-10-22","cited_by_count":14,"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":"2406.02395","title":"GrootVL: Tree Topology is All You Need in State Space Model","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2501.10891","title":"OpenEarthMap-SAR: A Benchmark Synthetic Aperture Radar Dataset for Global High-Resolution Land Cover Mapping","created":"2025-01-18","cited_by_count":13,"area":null},{"id":"2403.10935","title":"Understanding Robustness of Visual State Space Models for Image Classification","created":"2024-03-16","cited_by_count":12,"area":null},{"id":"2408.09743","title":"R2GenCSR: Mining Contextual and Residual Information for LLMs-based Radiology Report Generation","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2408.09764","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2410.14195","title":"Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2412.19225","title":"Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion","created":"2024-12-26","cited_by_count":12,"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":"2602.20160","title":"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction","created":"2026-02-23","cited_by_count":12,"area":null},{"id":"2404.03611","title":"InsectMamba: Insect Pest Classification with State Space Model","created":"2024-04-04","cited_by_count":11,"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":"2407.17801","title":"EEG-SSM: Leveraging State-Space Model for Dementia Detection","created":"2024-07-25","cited_by_count":11,"area":null},{"id":"2409.13094","title":"DenoMamba: A fused state-space model for low-dose CT denoising","created":"2024-09-19","cited_by_count":11,"area":null},{"id":"2411.17984","title":"RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2503.05578","title":"Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integration","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2508.04022","title":"Prototype-Driven Structure Synergy Network for Remote Sensing Images Segmentation","created":"2025-08-06","cited_by_count":11,"area":null},{"id":"2407.05128","title":"SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2502.00318","title":"Sub-Sequential Physics-Informed Learning with State Space Model","created":"2025-02-01","cited_by_count":10,"area":null},{"id":"2508.09454","title":"Animate-X++: Universal Character Image Animation with Dynamic Backgrounds","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2604.14816","title":"NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results","created":"2026-04-16","cited_by_count":10,"area":null},{"id":"2409.10699","title":"CoMamba: Real-time Cooperative Perception Unlocked with State Space Models","created":"2024-09-16","cited_by_count":9,"area":null},{"id":"2411.19455","title":"Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2412.17263","title":"VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling","created":"2024-12-23","cited_by_count":9,"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":"2406.13705","title":"EndoUIC: Promptable Diffusion Transformer for Unified Illumination Correction in Capsule Endoscopy","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2407.03535","title":"BVI-RLV: A Fully Registered Dataset for Low-Light Video Enhancement","created":"2024-07-03","cited_by_count":8,"area":null},{"id":"2407.11906","title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","created":"2024-07-16","cited_by_count":8,"area":null},{"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":"2412.09331","title":"Physics-Driven Autoregressive State Space Models for Medical Image Reconstruction","created":"2024-12-12","cited_by_count":8,"area":null},{"id":"2503.13858","title":"MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations","created":"2025-03-18","cited_by_count":8,"area":null},{"id":"2505.23248","title":"Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"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":"2404.17926","title":"Pre-training on High Definition X-ray Images: An Experimental Study","created":"2024-04-27","cited_by_count":7,"area":null},{"id":"2405.08419","title":"WaterMamba: Visual State Space Model for Underwater Image Enhancement","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2405.16470","title":"Image Deraining with Frequency-Enhanced State Space Model","created":"2024-05-26","cited_by_count":7,"area":null},{"id":"2405.16555","title":"Building Vision Models upon Heat Conduction","created":"2024-05-26","cited_by_count":7,"area":null},{"id":"2406.12463","title":"LFMamba: Light Field Image Super-Resolution with State Space Model","created":"2024-06-18","cited_by_count":7,"area":null},{"id":"2412.18177","title":"Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2504.18524","title":"Augmenting Perceptual Super-Resolution via Image Quality Predictors","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2601.06793","title":"CliffordNet: All You Need is Geometric Algebra","created":"2026-01-11","cited_by_count":7,"area":null},{"id":"2601.07832","title":"MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2604.21312","title":"The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview","created":"2026-04-23","cited_by_count":7,"area":null},{"id":"2404.05105","title":"VMambaMorph: a Multi-Modality Deformable Image Registration Framework based on Visual State Space Model with Cross-Scan Module","created":"2024-04-07","cited_by_count":6,"area":null},{"id":"2406.08444","title":"PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2408.01037","title":"MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection","created":"2024-08-02","cited_by_count":6,"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":"2410.04733","title":"Video Prediction Transformers without Recurrence or Convolution","created":"2024-10-07","cited_by_count":6,"area":null},{"id":"2503.14867","title":"DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2503.19331","title":"ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2507.03367","title":"Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices","created":"2025-07-04","cited_by_count":6,"area":null},{"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":"2509.15788","title":"FoBa: A Foreground-Background co-Guided Method and New Benchmark for Remote Sensing Semantic Change Detection","created":"2025-09-19","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":"2604.11564","title":"Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation","created":"2026-04-13","cited_by_count":6,"area":null},{"id":"2604.17306","title":"The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview","created":"2026-04-19","cited_by_count":6,"area":null},{"id":"2406.14086","title":"Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2502.00435","title":"SatMamba: Development of Foundation Models for Remote Sensing Imagery Using State Space Models","created":"2025-02-01","cited_by_count":5,"area":null},{"id":"2503.14493","title":"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2503.17984","title":"Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting","created":"2025-03-23","cited_by_count":5,"area":null}],"next_cursor":"100"}