{"total":70,"rows":[{"id":"2411.03670","title":"Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?","created":"2024-11-06","cited_by_count":31,"area":null},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"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":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"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":"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":"2512.12229","title":"Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder","created":"2025-12-13","cited_by_count":7,"area":null},{"id":"2602.17929","title":"ZACH-ViT: Regime-Dependent Inductive Bias in Compact Vision Transformers for Medical Imaging","created":"2026-02-20","cited_by_count":7,"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":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"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":"2501.12381","title":"Parallel Sequence Modeling via Generalized Spatial Propagation Network","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2504.05583","title":"Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2508.02168","title":"After the Party: Navigating the Mapping From Color to Ambient Lighting","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2502.18538","title":"Revisiting Convolution Architecture in the Realm of DNA Foundation Models","created":"2025-02-25","cited_by_count":3,"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":"2509.12817","title":"SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention","created":"2025-09-16","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":"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":"2511.09942","title":"AdaptViG: Adaptive Vision GNN with Exponential Decay Gating","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2511.12572","title":"Through-Foliage Surface-Temperature Reconstruction for Early Wildfire Detection","created":"2025-11-16","cited_by_count":2,"area":null},{"id":"2601.17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2605.21308","title":"Deformba: Vision State Space Model with Adaptive State Fusion","created":"2026-05-20","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":"2503.24166","title":"Foundation Models For Seismic Data Processing: An Extensive Review","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2507.09294","title":"Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2507.19807","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2511.07929","title":"Federated CLIP for Resource-Efficient Heterogeneous Medical Image Classification","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2512.07078","title":"DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.07385","title":"How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2602.00910","title":"Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2606.00906","title":"hZACH-ViT: Curved Latent Geometry for Compact Vision Transformers in Low-Data Medical Imaging","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.05999","title":"ATT-CR: Adaptive Triangular Transformer for Cloud Removal","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2408.04258","title":"UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network","created":"2024-08-08","cited_by_count":0,"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":"2501.18124","title":"REMOTE: Real-time Ego-motion Tracking for Various Endoscopes via Multimodal Visual Feature Learning","created":"2025-01-30","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":"2504.14832","title":"Protecting Your Voice: Temporal-aware Robust Watermarking","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2507.09940","title":"Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.15487","title":"DeSamba: Decoupled Spectral Adaptive Framework for 3D Multi-Sequence MRI Lesion Classification","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2508.12777","title":"SocialTrack: Multi-Object Tracking in Complex Urban Traffic Scenes Inspired by Social Behavior","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2508.17254","title":"A biological vision inspired framework for machine perception of abutting grating illusory contours","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2508.19850","title":"Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.02575","title":"The Lifecycle Principle: Stabilizing Dynamic Neural Networks with State Memory","created":"2025-08-24","cited_by_count":0,"area":null},{"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":"2510.06564","title":"HSNet: Heterogeneous Subgraph Network for Single Image Super-resolution","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.15439","title":"Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation","created":"2025-10-17","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":"2512.08647","title":"C-DIRA: Computationally Efficient Dynamic ROI Routing and Domain-Invariant Adversarial Learning for Lightweight Driver Behavior Recognition","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.23234","title":"Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2601.06443","title":"How to Build Robust, Scalable Models for GSV-Based Indicators in Neighborhood Research","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2601.08190","title":"Human-inspired Global-to-Parallel Multi-scale Encoding for Lightweight Vision Models","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2602.23903","title":"SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.01449","title":"Revisiting Global Token Mixing in Task-Dependent MRI Restoration: Insights from Minimal Gated CNN Baselines","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.25351","title":"Image Rotation Angle Estimation: Comparing Circular-Aware Methods","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2603.29732","title":"Compressive sensing inspired self-supervised single-pixel imaging","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.15711","title":"SSMamba: A Self-Supervised Hybrid State Space Model for Pathological Image Classification","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.02794","title":"Edge-Efficient Image Restoration: Transformer Distillation into State-Space Models","created":"2026-05-04","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":"2607.08379","title":"Classical Versus Deep Mirror-Symmetry Scoring: A Benchmark of Thirteen Methods","created":"2026-07-09","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":"2608.04442","title":"Robustness Emerges Early in Training Dynamics, but Is Not Preserved","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06712","title":"Suppress and Diversify: Refining Robust Pathways for Corruption Robustness","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.04390","title":"Development and Evaluation of Ultrasound Image Learning Pipelines for MASLD Risk Stratification","created":"2026-09-03","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":"2609.12408","title":"GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes","created":"2026-09-11","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}