{"total":108,"rows":[{"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":"2503.12461","title":"MambaIC: State Space Models for High-Performance Learned Image Compression","created":"2025-03-16","cited_by_count":20,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2509.00649","title":"MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation","created":"2025-08-31","cited_by_count":9,"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":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2507.10800","title":"ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2510.10982","title":"Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization","created":"2025-10-13","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":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2409.08688","title":"GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Construction","created":"2024-09-13","cited_by_count":4,"area":null},{"id":"2501.12381","title":"Parallel Sequence Modeling via Generalized Spatial Propagation Network","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2503.06369","title":"Spectral State Space Model for Rotation-Invariant Visual Representation Learning","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2503.12355","title":"Atlas: Multi-Scale Attention Improves Long Context Image Modeling","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2504.07395","title":"FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2411.12635","title":"M3D: Dual-Stream Selective State Spaces and Depth-Driven Framework for High-Fidelity Single-View 3D Reconstruction","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2509.20006","title":"Revisiting Image Manipulation Localization under Realistic Manipulation Scenarios","created":"2025-09-24","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":"2512.09383","title":"Perception-Inspired Color Space Design for Photo White Balance Editing","created":"2025-12-10","cited_by_count":2,"area":null},{"id":"2602.20981","title":"Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2408.11679","title":"BadVim: Unveiling Backdoor Threats in Visual State Space Model","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2411.13181","title":"Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2502.18225","title":"Liver Cirrhosis Stage Estimation from MRI with Deep Learning","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2506.15940","title":"Polyline Path Masked Attention for Vision Transformer","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2507.17479","title":"SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2507.20765","title":"Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2508.00383","title":"$MV_{Hybrid}$: Improving Spatial Transcriptomics Prediction with Hybrid State Space-Vision Transformer Backbone in Pathology Vision Foundation Models","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2508.11531","title":"Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction","created":"2025-08-15","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":"2511.06897","title":"Adaptive Morph-Patch Transformer for Aortic Vessel Segmentation","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2511.16428","title":"CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2511.16541","title":"Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution","created":"2025-11-20","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":"2602.08126","title":"MambaFusion: Adaptive State-Space Fusion for Multimodal 3D Object Detection","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2603.19567","title":"Efficiency Follows Global-Local Decoupling","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.19684","title":"TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.25220","title":"Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.14251","title":"HiST: A Hierarchical Sparse Transformer for Cross-Modal Spatial Transcriptomics Modeling","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.02158","title":"Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.04403","title":"MambaRefine-CD: MambaVision with Region-Boundary Temporal Refinement","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2608.13783","title":"Doomed to Re-Annotate, Forever: The ImageNet Story","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2410.03174","title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","created":"2024-10-04","cited_by_count":0,"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":"2501.00619","title":"A Study on Context Length and Efficient Transformers for Biomedical Image Analysis","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2501.07533","title":"Confident Pseudo-labeled Diffusion Augmentation for Canine Cardiomegaly Detection","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2502.07120","title":"Is Long Range Sequential Modeling Necessary For Colorectal Tumor Segmentation?","created":"2025-02-10","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":"2504.18594","title":"RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruning","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2505.01656","title":"WaveInst: A Frequency-Domain Enhanced Network for Fine-Grained Thin Tree Trunk Extraction in Forest Scenes","created":"2025-05-03","cited_by_count":0,"area":null},{"id":"2505.12638","title":"ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2505.18604","title":"Exemplar-Free Continual Learning for State Space Models","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2506.18248","title":"Improving Black-Box Generative Attacks via Generator Semantic Consistency","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2506.22498","title":"ViFusionTST: Deep Fusion of Time-Series Image Representations from Load Signals for Early Bed-Exit Prediction","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2507.11549","title":"A Memory-Efficient Framework for Deformable Transformer with Neural Architecture Search","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2507.20017","title":"VAMPIRE: Uncovering Vessel Directional and Morphological Information from OCTA Images for Cardiovascular Disease Risk Factor Prediction","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2508.08700","title":"Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.11921","title":"ENA: Efficient N-dimensional Attention","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2509.02261","title":"DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2509.13713","title":"UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2510.16209","title":"StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.22208","title":"Simplifying Knowledge Transfer in Pretrained Models","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2511.00004","title":"Multimodal Learning with Augmentation Techniques for Natural Disaster Assessment","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2511.13487","title":"Systematic Evaluation of Time-Frequency Features for Binaural Sound Source Localization","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2511.14792","title":"Application of Graph Based Vision Transformers Architectures for Accurate Temperature Prediction in Fiber Specklegram Sensors","created":"2025-11-15","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":"2512.07884","title":"GSPN-2: Efficient Parallel Sequence Modeling","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.18407","title":"Through the PRISm: Importance-Aware Scene Graphs for Image Retrieval","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2512.23160","title":"A Weak Signal Learning Dataset and Its Baseline Method","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2603.00175","title":"Self-Attention And Beyond the Infinite: Towards Linear Transformers with Infinite Self-Attention","created":"2026-02-26","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":"2603.05114","title":"UniPAR: A Unified Framework for Pedestrian Attribute Recognition","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.07819","title":"Fusion Complexity Is Not Fusion Quality: Backbone, Cross View Fusion and Metadata as Separate Factors in Pasture Biomass Regression","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.07920","title":"RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.09037","title":"WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.19209","title":"Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.23669","title":"Estimating Individual Tree Height and Species from UAV Imagery","created":"2026-03-24","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":"2604.01581","title":"Satellite-Free Training for Drone-View Geo-Localization","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.23320","title":"KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2604.27654","title":"MSR:Hybrid Field Modeling for CT-MRI Rigid-Deformable Registration of the Cervical Spine with an Annotated Dataset","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.05616","title":"RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.07151","title":"DPG-CD: Depth-Prior-Guided Cross-Modal Joint 2D-3D Change Detection","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.07338","title":"ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs","created":"2026-05-08","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":"2605.19734","title":"GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.15287","title":"G2IA: Geometry-Guided Instance-Aware Retrieval and Refinement for Cross-Modal Place Recognition","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.27718","title":"MASS: Motion-Aligned Selective Scan for Refinement in Flow-Based Video Frame Interpolation","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.29029","title":"Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.00057","title":"Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.00369","title":"SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.06918","title":"LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.10777","title":"RED-Sphere: Hyperspherical Residual Edge Debiasing for Cross-Population Fundus Disease Domain Generalization","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.10995","title":"AsySplat: Efficient Asymmetric 3D Gaussian Splatting for Long-Sequence Scene Modeling","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.11099","title":"Desc++: Efficient Descriptor Enhancement for Data Association in Existing Visual SLAM Systems","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.17208","title":"Induce to Empower: Improving Lightweight Baselines via Foundation Model Induction for Generalized Polyp Segmentation","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.23633","title":"A Controlled Visual-Backbone Benchmark for Multimodal Short-Term Solar Irradiance Forecasting","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.25988","title":"Generator-Aligned Representation Interfaces for Diagnostic Soft Equivariance","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.09801","title":"Modern Backbones Improve Multi-task DETR for Mammography Classification and Lesion Localization","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.30094","title":"A Hybrid State-Space Approach for Census-Tract Population Estimation","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":"100"}