{"total":45,"rows":[{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68,"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":"2311.17132","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2403.19967","title":"Rewrite the Stars","created":"2024-03-29","cited_by_count":55,"area":null},{"id":"2404.01547","title":"Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining","created":"2024-04-02","cited_by_count":54,"area":null},{"id":"2411.07635","title":"Breaking the Low-Rank Dilemma of Linear Attention","created":"2024-11-12","cited_by_count":31,"area":null},{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2407.17261","title":"Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation","created":"2024-07-24","cited_by_count":14,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2509.18493","title":"MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation","created":"2025-09-23","cited_by_count":12,"area":null},{"id":"2512.07348","title":"MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition","created":"2025-12-08","cited_by_count":10,"area":null},{"id":"2310.05393","title":"Hierarchical Side-Tuning for Vision Transformers","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2412.10943","title":"Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes","created":"2024-12-14","cited_by_count":7,"area":null},{"id":"2404.05196","title":"HSViT: Horizontally Scalable Vision Transformer","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2405.13335","title":"Vision Transformer with Sparse Scan Prior","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2405.13337","title":"Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2409.10890","title":"SkinMamba: A Precision Skin Lesion Segmentation Architecture with Cross-Scale Global State Modeling and Frequency Boundary Guidance","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2508.09000","title":"UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","created":"2025-08-12","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":"2407.13920","title":"DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2409.07896","title":"MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space Models","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2410.15279","title":"ContextDet: Temporal Action Detection with Adaptive Context Aggregation","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2411.17061","title":"SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation","created":"2024-11-26","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":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2410.24139","title":"COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2501.09221","title":"ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2505.08231","title":"HMPNet: A Feature Aggregation Architecture for Maritime Object Detection from a Shipborne Perspective","created":"2025-05-13","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":"2512.12941","title":"UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction","created":"2025-12-15","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":"2312.06955","title":"IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2409.06963","title":"Brain-Inspired Stepwise Patch Merging for Vision Transformers","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2411.02747","title":"Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2411.15799","title":"Symmetric Perception and Ordinal Regression for Detecting Scoliosis Natural Image","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2412.02197","title":"Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2503.20382","title":"RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2506.12982","title":"DuoFormer: Leveraging Hierarchical Representations by Local and Global Attention Vision Transformer","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2507.12125","title":"Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2510.26315","title":"A Hybrid Framework Bridging CNN and ViT based on Theory of Evidence for Diabetic Retinopathy Grading","created":"2025-10-30","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":"2604.16147","title":"SWNet: A Cross-Spectral Network for Camouflaged Weed Detection","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.18549","title":"Advancing Vision Transformer with Enhanced Spatial Priors","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.21970","title":"Entropy-Guided Self-Supervised Learning for Medical Image Classification","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.03945","title":"A Large-Scale Dataset and a New Method for RemoteSensing Traffic Object Segmentation","created":"2026-07-04","cited_by_count":0,"area":null}],"next_cursor":null}