{"total":172,"rows":[{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712,"area":null},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310,"area":null},{"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":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2103.10596","title":"PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization","created":"2021-03-19","cited_by_count":133,"area":null},{"id":"2212.00968","title":"UIU-Net: U-Net in U-Net for Infrared Small Object Detection","created":"2022-12-02","cited_by_count":127,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2111.14556","title":"On the Integration of Self-Attention and Convolution","created":"2021-11-29","cited_by_count":74,"area":null},{"id":"2304.10244","title":"Omni Aggregation Networks for Lightweight Image Super-Resolution","created":"2023-04-20","cited_by_count":62,"area":null},{"id":"2209.07947","title":"Omni-Dimensional Dynamic Convolution","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2104.14107","title":"Decoupled Dynamic Filter Networks","created":"2021-04-29","cited_by_count":53,"area":null},{"id":"2101.00590","title":"RegNet: Self-Regulated Network for Image Classification","created":"2021-01-03","cited_by_count":44,"area":null},{"id":"2104.14783","title":"BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification","created":"2021-04-30","cited_by_count":44,"area":null},{"id":"2206.00388","title":"Transfer without Forgetting","created":"2022-06-01","cited_by_count":44,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2107.00782","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","created":"2021-07-02","cited_by_count":39,"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":"2104.13497","title":"ConTNet: Why not use convolution and transformer at the same time?","created":"2021-04-27","cited_by_count":38,"area":null},{"id":"2106.03180","title":"Vision Transformers with Hierarchical Attention","created":"2021-06-06","cited_by_count":31,"area":null},{"id":"2110.05741","title":"Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization","created":"2021-10-12","cited_by_count":30,"area":null},{"id":"2112.06988","title":"Event-guided Deblurring of Unknown Exposure Time Videos","created":"2021-12-13","cited_by_count":26,"area":null},{"id":"2405.06284","title":"Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention","created":"2024-05-10","cited_by_count":26,"area":null},{"id":"2209.14498","title":"Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition","created":"2022-09-29","cited_by_count":22,"area":"distill"},{"id":"2303.08050","title":"Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Images","created":"2023-03-14","cited_by_count":21,"area":null},{"id":"2104.09497","title":"Attention in Attention Network for Image Super-Resolution","created":"2021-04-19","cited_by_count":20,"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":"2107.05630","title":"Challenges for machine learning in clinical translation of big data imaging studies","created":"2021-07-07","cited_by_count":15,"area":null},{"id":"2309.09306","title":"Effective Image Tampering Localization via Enhanced Transformer and Co-attention Fusion","created":"2023-09-17","cited_by_count":15,"area":null},{"id":"2409.14028","title":"MSDet: Receptive Field Enhanced Multiscale Detection for Tiny Pulmonary Nodule","created":"2024-09-21","cited_by_count":14,"area":null},{"id":"2106.03959","title":"Generative Flows with Invertible Attentions","created":"2021-06-07","cited_by_count":13,"area":null},{"id":"2210.06361","title":"MFFN: Multi-view Feature Fusion Network for Camouflaged Object Detection","created":"2022-10-12","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":"2201.12903","title":"Aggregating Global Features into Local Vision Transformer","created":"2022-01-30","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":"2102.07037","title":"Robust Lane Detection via Expanded Self Attention","created":"2021-02-14","cited_by_count":9,"area":null},{"id":"2106.08615","title":"EdgeConv with Attention Module for Monocular Depth Estimation","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2112.04150","title":"BA-Net: Bridge Attention for Deep Convolutional Neural Networks","created":"2021-12-08","cited_by_count":9,"area":null},{"id":"2308.09939","title":"Understanding Self-attention Mechanism via Dynamical System Perspective","created":"2023-08-19","cited_by_count":9,"area":null},{"id":"2103.13389","title":"Generating Novel Scene Compositions from Single Images and Videos","created":"2021-03-24","cited_by_count":8,"area":null},{"id":"2201.09271","title":"Wavelet-Attention CNN for Image Classification","created":"2022-01-23","cited_by_count":8,"area":null},{"id":"2211.02299","title":"GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoff","created":"2022-11-04","cited_by_count":8,"area":null},{"id":"2401.00833","title":"Rethinking RAFT for Efficient Optical Flow","created":"2024-01-01","cited_by_count":8,"area":null},{"id":"2403.01123","title":"ELA: Efficient Local Attention for Deep Convolutional Neural Networks","created":"2024-03-02","cited_by_count":8,"area":null},{"id":"2101.03929","title":"ORDNet: Capturing Omni-Range Dependencies for Scene Parsing","created":"2021-01-11","cited_by_count":7,"area":null},{"id":"2201.07124","title":"Attentional Feature Refinement and Alignment Network for Aircraft Detection in SAR Imagery","created":"2022-01-18","cited_by_count":7,"area":null},{"id":"2203.10489","title":"TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing","created":"2022-03-20","cited_by_count":7,"area":null},{"id":"2207.11225","title":"Large-Kernel Attention for 3D Medical Image Segmentation","created":"2022-07-19","cited_by_count":7,"area":null},{"id":"2311.04942","title":"CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image Segmentation","created":"2023-11-08","cited_by_count":7,"area":null},{"id":"2402.09329","title":"YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection","created":"2024-02-14","cited_by_count":7,"area":null},{"id":"2201.01427","title":"Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation","created":"2022-01-05","cited_by_count":6,"area":null},{"id":"2307.14446","title":"Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach","created":"2023-07-26","cited_by_count":6,"area":null},{"id":"2309.15697","title":"Physics Inspired Hybrid Attention for SAR Target Recognition","created":"2023-09-27","cited_by_count":6,"area":null},{"id":"1907.06838","title":"Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving","created":"2019-07-16","cited_by_count":5,"area":"offlinerl"},{"id":"2101.00652","title":"Depth as Attention for Face Representation Learning","created":"2021-01-03","cited_by_count":5,"area":null},{"id":"2103.15099","title":"BA^2M: A Batch Aware Attention Module for Image Classification","created":"2021-03-28","cited_by_count":5,"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":"2210.16101","title":"A Generic Shared Attention Mechanism for Various Backbone Neural Networks","created":"2022-10-27","cited_by_count":5,"area":null},{"id":"2403.20225","title":"MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2409.18826","title":"YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detection","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2110.01825","title":"Attention Augmented Convolutional Transformer for Tabular Time-series","created":"2021-10-05","cited_by_count":4,"area":null},{"id":"2111.13470","title":"TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2203.15285","title":"Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching","created":"2022-03-29","cited_by_count":4,"area":null},{"id":"2209.05680","title":"Switchable Self-attention Module","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2304.00280","title":"Progressive Channel-Shrinking Network","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2308.08361","title":"KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution","created":"2023-08-16","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":"2404.12037","title":"Data-free Knowledge Distillation for Fine-grained Visual Categorization","created":"2024-04-18","cited_by_count":4,"area":"distill"},{"id":"2406.01833","title":"CAFO: Feature-Centric Explanation on Time Series Classification","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2508.03625","title":"AttZoom: Attention Zoom for Better Visual Features","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2105.05847","title":"Learning to Generate Novel Scene Compositions from Single Images and Videos","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2108.08205","title":"An Attention Module for Convolutional Neural Networks","created":"2021-08-18","cited_by_count":3,"area":null},{"id":"2302.05213","title":"CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2303.11055","title":"Parameter-Free Channel Attention for Image Classification and Super-Resolution","created":"2023-03-20","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":"2402.02094","title":"Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification","created":"2024-02-03","cited_by_count":3,"area":null},{"id":"2403.05451","title":"Attention-guided Feature Distillation for Semantic Segmentation","created":"2024-03-08","cited_by_count":3,"area":"distill"},{"id":"2411.01988","title":"QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2412.01202","title":"Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2503.06473","title":"Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2105.14824","title":"Bounded logit attention: Learning to explain image classifiers","created":"2021-05-31","cited_by_count":2,"area":null},{"id":"2107.12560","title":"Perception-and-Regulation Network for Salient Object Detection","created":"2021-07-27","cited_by_count":2,"area":null},{"id":"2110.04954","title":"Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2207.11393","title":"Deep Pneumonia: Attention-Based Contrastive Learning for Class-Imbalanced Pneumonia Lesion Recognition in Chest X-rays","created":"2022-07-23","cited_by_count":2,"area":null},{"id":"2212.06335","title":"CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion","created":"2022-12-13","cited_by_count":2,"area":null},{"id":"2304.06345","title":"ASR: Attention-alike Structural Re-parameterization","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2305.10126","title":"Fusion-S2iGan: An Efficient and Effective Single-Stage Framework for Speech-to-Image Generation","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2309.10219","title":"Multi-level feature fusion network combining attention mechanisms for polyp segmentation","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2312.08020","title":"Generalized Deepfakes Detection with Reconstructed-Blended Images and Multi-scale Feature Reconstruction Network","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2401.04560","title":"Phase-shifted remote photoplethysmography for estimating heart rate and blood pressure from facial video","created":"2024-01-09","cited_by_count":2,"area":null},{"id":"2403.01713","title":"MCA: Moment Channel Attention Networks","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2503.00250","title":"Solar Multimodal Transformer: Intraday Solar Irradiance Predictor using Public Cameras and Time Series","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2506.05041","title":"DACN: Dual-Attention Convolutional Network for Hyperspectral Image Super-Resolution","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2105.13153","title":"Cardiac Segmentation on CT Images through Shape-Aware Contour Attentions","created":"2021-05-27","cited_by_count":1,"area":null},{"id":"2106.10920","title":"Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification","created":"2021-06-21","cited_by_count":1,"area":null},{"id":"2111.00398","title":"A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones","created":"2021-10-31","cited_by_count":1,"area":null},{"id":"2112.06132","title":"Periodic Residual Learning for Crowd Flow Forecasting","created":"2021-12-08","cited_by_count":1,"area":null},{"id":"2201.00467","title":"maskGRU: Tracking Small Objects in the Presence of Large Background Motions","created":"2022-01-03","cited_by_count":1,"area":null},{"id":"2211.13808","title":"Detecting Anomalies using Generative Adversarial Networks on Images","created":"2022-11-24","cited_by_count":1,"area":null}],"next_cursor":"100"}