{"total":59,"rows":[{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"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":"2411.07635","title":"Breaking the Low-Rank Dilemma of Linear Attention","created":"2024-11-12","cited_by_count":31,"area":null},{"id":"2504.04701","title":"DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation","created":"2025-04-07","cited_by_count":31,"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":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2503.16067","title":"Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures","created":"2025-03-20","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":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2405.13335","title":"Vision Transformer with Sparse Scan Prior","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2311.16673","title":"Large Language Models Meet Computer Vision: A Brief Survey","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2401.10110","title":"SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor","created":"2024-01-18","cited_by_count":5,"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":"2411.04967","title":"AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2409.07995","title":"Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes","created":"2024-09-12","cited_by_count":3,"area":null},{"id":"2505.16463","title":"AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer","created":"2025-05-22","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":"2402.00534","title":"A Manifold Representation of the Key in Vision Transformers","created":"2024-02-01","cited_by_count":2,"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":"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":"2310.05446","title":"RetSeg: Retention-based Colorectal Polyps Segmentation Network","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2405.07524","title":"HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2407.05562","title":"Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2505.08437","title":"TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery Detection","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2505.16372","title":"Temporal and Spatial Feature Fusion Framework for Dynamic Micro Expression Recognition","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.12836","title":"HyRet-Change: A hybrid retentive network for remote sensing change detection","created":"2025-06-15","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":"2508.09525","title":"Learning Spatial Decay for Vision Transformers","created":"2025-08-13","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":"2602.17387","title":"DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2609.29064","title":"EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection","created":"2026-09-24","cited_by_count":1,"area":null},{"id":"2404.15451","title":"CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2409.04025","title":"BFA-YOLO: A balanced multiscale object detection network for building fa\\c{c}ade attachments detection","created":"2024-09-06","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":"2503.11995","title":"Fraesormer: Learning Adaptive Sparse Transformer for Efficient Food Recognition","created":"2025-03-15","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":"2504.12923","title":"Efficient Masked Image Compression with Position-Indexed Self-Attention","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2504.17834","title":"Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.06708","title":"A Survey of Retentive Network","created":"2025-06-07","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":"2507.08637","title":"Scaling Attention to Very Long Sequences in Linear Time with Wavelet-Enhanced Random Spectral Attention (WERSA)","created":"2025-07-11","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":"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":"2601.16428","title":"DCCS-Det: Directional Context and Cross-Scale-Aware Detector for Infrared Small Target","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2602.04346","title":"MirrorLA: Reflecting Feature Map for Vision Linear Attention","created":"2026-02-04","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":"2603.00486","title":"Random Wins All: Rethinking Grouping Strategies for Vision Tokens","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2603.21626","title":"PGR-Net: Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.06014","title":"Gated-SwinRMT: Unifying Swin Windowed Attention with Retentive Manhattan Decay via Input-Dependent Gating","created":"2026-04-07","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":"2605.11555","title":"ScribbleDose: Scribble-Guided Dose Prediction in Radiotherapy","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.20839","title":"Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.14757","title":"Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.27226","title":"DINOcular: Self-Supervised Visuospatial Representations","created":"2026-08-27","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}