{"total":75,"rows":[{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2109.07270","title":"Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition","created":"2021-09-15","cited_by_count":55,"area":null},{"id":"2209.07947","title":"Omni-Dimensional Dynamic Convolution","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2104.14854","title":"NTIRE 2021 Challenge on Image Deblurring","created":"2021-04-30","cited_by_count":50,"area":null},{"id":"2304.12489","title":"Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection","created":"2023-04-24","cited_by_count":50,"area":null},{"id":"2203.12198","title":"Deep Frequency Filtering for Domain Generalization","created":"2022-03-23","cited_by_count":43,"area":null},{"id":"2305.13563","title":"Efficient Multi-Scale Attention Module with Cross-Spatial Learning","created":"2023-05-23","cited_by_count":41,"area":null},{"id":"2112.05561","title":"Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions","created":"2021-12-10","cited_by_count":39,"area":null},{"id":"2111.00454","title":"Gaussian Kernel Mixture Network for Single Image Defocus Deblurring","created":"2021-10-31","cited_by_count":20,"area":null},{"id":"2203.09694","title":"Group Contextualization for Video Recognition","created":"2022-03-18","cited_by_count":18,"area":null},{"id":"2105.14447","title":"EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network","created":"2021-05-30","cited_by_count":15,"area":null},{"id":"2204.09303","title":"Attention in Attention: Modeling Context Correlation for Efficient Video Classification","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2403.17701","title":"Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentation","created":"2024-03-26","cited_by_count":12,"area":"ssm"},{"id":"2304.03198","title":"RFAConv: Receptive-Field Attention Convolution for Improving Convolutional Neural Networks","created":"2023-04-06","cited_by_count":10,"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":"2110.14787","title":"SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata","created":"2021-10-27","cited_by_count":9,"area":null},{"id":"2111.12419","title":"NAM: Normalization-based Attention Module","created":"2021-11-24","cited_by_count":8,"area":null},{"id":"2506.21364","title":"CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2406.02976","title":"DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2208.09211","title":"Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention","created":"2022-08-19","cited_by_count":5,"area":null},{"id":"2304.12235","title":"Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2312.08866","title":"MCANet: Medical Image Segmentation with Multi-Scale Cross-Axis Attention","created":"2023-12-14","cited_by_count":5,"area":null},{"id":"2106.11447","title":"Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation","created":"2021-06-21","cited_by_count":4,"area":null},{"id":"2108.11695","title":"PAENet: A Progressive Attention-Enhanced Network for 3D to 2D Retinal Vessel Segmentation","created":"2021-08-26","cited_by_count":4,"area":null},{"id":"2112.12748","title":"Assessing the Impact of Attention and Self-Attention Mechanisms on the Classification of Skin Lesions","created":"2021-12-23","cited_by_count":4,"area":null},{"id":"2308.11757","title":"Weakly Supervised Face and Whole Body Recognition in Turbulent Environments","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2403.19882","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2107.02145","title":"Tiled Squeeze-and-Excite: Channel Attention With Local Spatial Context","created":"2021-07-05","cited_by_count":3,"area":null},{"id":"2310.15648","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2312.09743","title":"SLS4D: Sparse Latent Space for 4D Novel View Synthesis","created":"2023-12-15","cited_by_count":3,"area":null},{"id":"2409.02546","title":"Real-Time Dynamic Scale-Aware Fusion Detection Network: Take Road Damage Detection as an example","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2502.03649","title":"All-in-One Image Compression and Restoration","created":"2025-02-05","cited_by_count":3,"area":null},{"id":"2306.01562","title":"An Attentive-based Generative Model for Medical Image Synthesis","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2402.13737","title":"RNDiff: Rainfall nowcasting with Condition Diffusion Model","created":"2024-02-21","cited_by_count":2,"area":"diffusion"},{"id":"2408.03030","title":"Nighttime Pedestrian Detection Based on Fore-Background Contrast Learning","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2504.20306","title":"Dynamic Contextual Attention Network: Transforming Spatial Representations into Adaptive Insights for Endoscopic Polyp Diagnosis","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2109.07373","title":"A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks","created":"2021-09-15","cited_by_count":1,"area":null},{"id":"2204.01513","title":"Context-aware Visual Tracking with Joint Meta-updating","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2205.13124","title":"PixelGame: Infrared small target segmentation as a Nash equilibrium","created":"2022-05-26","cited_by_count":1,"area":null},{"id":"2310.19835","title":"CrossEAI: Using Explainable AI to generate better bounding boxes for Chest X-ray images","created":"2023-10-29","cited_by_count":1,"area":null},{"id":"2311.03071","title":"OrthoNets: Orthogonal Channel Attention Networks","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2401.06995","title":"A Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler","created":"2024-01-13","cited_by_count":1,"area":null},{"id":"2402.09101","title":"DestripeCycleGAN: Stripe Simulation CycleGAN for Unsupervised Infrared Image Destriping","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2404.08917","title":"MAProtoNet: A Multi-scale Attentive Interpretable Prototypical Part Network for 3D Magnetic Resonance Imaging Brain Tumor Classification","created":"2024-04-13","cited_by_count":1,"area":null},{"id":"2405.11682","title":"FADet: A Multi-sensor 3D Object Detection Network based on Local Featured Attention","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2504.05779","title":"FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2602.11066","title":"PuriLight: A Lightweight Shuffle and Purification Framework for Monocular Depth Estimation","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.11717","title":"COTONET: A custom cotton detection algorithm based on YOLO11 for stage of growth cotton boll detection","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2106.06996","title":"Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution","created":"2021-06-13","cited_by_count":0,"area":null},{"id":"2305.10442","title":"CBAGAN-RRT: Convolutional Block Attention Generative Adversarial Network for Sampling-Based Path Planning","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2306.14104","title":"A Novel Dual-pooling Attention Module for UAV Vehicle Re-identification","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2311.12091","title":"DAS: A Deformable Attention to Capture Salient Information in CNNs","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2401.06999","title":"Datasets, Clues and State-of-the-Arts for Multimedia Forensics: An Extensive Review","created":"2024-01-13","cited_by_count":0,"area":null},{"id":"2406.19672","title":"Beyond First-Order: A Multi-Scale Approach to Finger Knuckle Print Biometrics","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2407.09530","title":"Optimization of Autonomous Driving Image Detection Based on RFAConv and Triplet Attention","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2410.07860","title":"BA-Net: Bridge Attention in Deep Neural Networks","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2411.14002","title":"SEMPose: A Single End-to-end Network for Multi-object Pose Estimation","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2411.14781","title":"Reconciling Semantic Controllability and Diversity for Remote Sensing Image Synthesis with Hybrid Semantic Embedding","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2412.14833","title":"Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2502.05988","title":"SNAT-YOLO: Efficient Cross-Layer Aggregation Network for Edge-Oriented Gangue Detection","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2504.19080","title":"MIA-Mind: A Multidimensional Interactive Attention Mechanism Based on MindSpore","created":"2025-04-27","cited_by_count":0,"area":null},{"id":"2505.05943","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2505.08568","title":"Thermal Detection of People with Mobility Restrictions for Barrier Reduction at Traffic Lights Controlled Intersections","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2506.03171","title":"EdgeVidSum: Real-Time Personalized Video Summarization at the Edge","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2509.10024","title":"Hierarchical MLANet: Multi-level Attention for 3D Face Reconstruction From Single Images","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2509.13735","title":"State Space Models over Directed Graphs","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2511.01546","title":"PCD-ReID: Occluded Person Re-Identification for Base Station Inspection","created":"2025-11-03","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":"2601.16617","title":"Boundary and Position Information Mining for Aerial Small Object Detection","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2605.08592","title":"Cross-Modal RGB-D Fusion Transformer for 6D Pose Estimation of Non-Cooperative Spacecraft with Stereo-Derived Depth","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.15118","title":"Multi-view feature High-order Fusion for Space Weak Object Detection and Segmentation","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.02360","title":"GAP-GDRNet: Geometry-aware monocular 6D pose estimation for spacecraft using synthetic geometric supervision","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.09774","title":"C$^2$A: Coupling Spatial Evidence with Clinical Priors via Co-occurrence Aware Class Attention for Multi-Label Chest X-Ray Classification","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.05070","title":"MultiAttenGastro: Multi-Dimensional Attention Augmentation for Gastrointestinal Endoscopy Classification","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}