{"total":99,"rows":[{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"area":null},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"area":null},{"id":"2106.00515","title":"KVT: k-NN Attention for Boosting Vision Transformers","created":"2021-05-28","cited_by_count":65,"area":null},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","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":"2404.10343","title":"The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report","created":"2024-04-16","cited_by_count":57,"area":null},{"id":"2203.02452","title":"Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression","created":"2022-03-04","cited_by_count":45,"area":null},{"id":"2204.02557","title":"MixFormer: Mixing Features across Windows and Dimensions","created":"2022-04-06","cited_by_count":43,"area":null},{"id":"2305.05813","title":"Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review","created":"2023-05-09","cited_by_count":41,"area":null},{"id":"2309.02031","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","created":"2023-09-05","cited_by_count":41,"area":null},{"id":"2106.12378","title":"Co-advise: Cross Inductive Bias Distillation","created":"2021-06-23","cited_by_count":40,"area":null},{"id":"2106.01401","title":"Container: Context Aggregation Network","created":"2021-06-02","cited_by_count":37,"area":null},{"id":"2103.06564","title":"PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation","created":"2021-03-11","cited_by_count":29,"area":null},{"id":"2109.03810","title":"Scaled ReLU Matters for Training Vision Transformers","created":"2021-09-08","cited_by_count":29,"area":null},{"id":"2211.12051","title":"Adaptive Dynamic Filtering Network for Image Denoising","created":"2022-11-22","cited_by_count":28,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2504.10686","title":"The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report","created":"2025-04-14","cited_by_count":26,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2404.07543","title":"Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2503.18783","title":"Frequency Dynamic Convolution for Dense Image Prediction","created":"2025-03-24","cited_by_count":19,"area":null},{"id":"2112.12786","title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","created":"2021-12-23","cited_by_count":18,"area":null},{"id":"2307.08500","title":"Cumulative Spatial Knowledge Distillation for Vision Transformers","created":"2023-07-17","cited_by_count":18,"area":"distill"},{"id":"2405.13194","title":"KPConvX: Modernizing Kernel Point Convolution with Kernel Attention","created":"2024-05-21","cited_by_count":16,"area":null},{"id":"2111.01673","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","created":"2021-11-02","cited_by_count":15,"area":null},{"id":"2409.19833","title":"HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes","created":"2024-09-30","cited_by_count":15,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2308.02620","title":"Frequency Disentangled Features in Neural Image Compression","created":"2023-08-04","cited_by_count":14,"area":null},{"id":"2206.04665","title":"AGConv: Adaptive Graph Convolution on 3D Point Clouds","created":"2022-06-09","cited_by_count":13,"area":null},{"id":"2306.12992","title":"Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers","created":"2023-06-22","cited_by_count":13,"area":null},{"id":"2106.15338","title":"Probabilistic Attention for Interactive Segmentation","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2309.16393","title":"HIC-YOLOv5: Improved YOLOv5 For Small Object Detection","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2106.02253","title":"X-volution: On the unification of convolution and self-attention","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2203.00047","title":"Local and Global GANs with Semantic-Aware Upsampling for Image Generation","created":"2022-02-28","cited_by_count":8,"area":null},{"id":"2308.06707","title":"Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition","created":"2023-08-13","cited_by_count":8,"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":"2201.00392","title":"Fast and High-Quality Image Denoising via Malleable Convolutions","created":"2022-01-02","cited_by_count":6,"area":null},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2303.06316","title":"One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks","created":"2023-03-11","cited_by_count":6,"area":null},{"id":"2307.00592","title":"X-MLP: A Patch Embedding-Free MLP Architecture for Vision","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2311.11587","title":"LDConv: Linear deformable convolution for improving convolutional neural networks","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2406.07879","title":"KernelWarehouse: Rethinking the Design of Dynamic Convolution","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2409.04714","title":"Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection","created":"2024-09-07","cited_by_count":6,"area":null},{"id":"2110.08814","title":"TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding","created":"2021-10-17","cited_by_count":5,"area":null},{"id":"2303.17803","title":"Rethinking Local Perception in Lightweight Vision Transformer","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2304.03481","title":"PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift","created":"2023-04-07","cited_by_count":5,"area":null},{"id":"2308.03200","title":"Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network","created":"2023-08-06","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":"2401.03575","title":"Involution Fused ConvNet for Classifying Eye-Tracking Patterns of Children with Autism Spectrum Disorder","created":"2024-01-07","cited_by_count":4,"area":null},{"id":"2211.14576","title":"CFNet: Conditional Filter Learning with Dynamic Noise Estimation for Real Image Denoising","created":"2022-11-26","cited_by_count":2,"area":null},{"id":"2212.08330","title":"Convolution-enhanced Evolving Attention Networks","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2305.14409","title":"Evolution: A Unified Formula for Feature Operators from a High-level Perspective","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2309.10713","title":"Interpret Vision Transformers as ConvNets with Dynamic Convolutions","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2403.06676","title":"CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2201.10471","title":"GIU-GANs: Global Information Utilization for Generative Adversarial Networks","created":"2022-01-25","cited_by_count":1,"area":null},{"id":"2205.00932","title":"Understanding CNNs from excitations","created":"2022-05-02","cited_by_count":1,"area":null},{"id":"2211.16289","title":"Lightweight Structure-Aware Attention for Visual Understanding","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2304.07741","title":"Canvas: End-to-End Kernel Architecture Search in Neural Networks","created":"2023-04-16","cited_by_count":1,"area":null},{"id":"2306.03373","title":"CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2306.04086","title":"TEC-Net: Vision Transformer Embrace Convolutional Neural Networks for Medical Image Segmentation","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2307.15778","title":"Spherical and Hyperbolic Toric Topology-Based Codes On Graph Embedding for Ising MRF Models: Classical and Quantum Topology Machine Learning","created":"2023-07-28","cited_by_count":1,"area":null},{"id":"2311.02855","title":"Neural-based Compression Scheme for Solar Image Data","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2401.06998","title":"Towards Effective Image Forensics via A Novel Computationally Efficient Framework and A New Image Splice Dataset","created":"2024-01-13","cited_by_count":1,"area":null},{"id":"2409.18506","title":"Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2411.00485","title":"LAM-YOLO: Drones-based Small Object Detection on Lighting-Occlusion Attention Mechanism YOLO","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2502.03772","title":"A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinoma","created":"2025-02-06","cited_by_count":1,"area":"moe"},{"id":"2201.01983","title":"Multi-Domain Joint Training for Person Re-Identification","created":"2022-01-06","cited_by_count":0,"area":null},{"id":"2202.01926","title":"Knowledge Graph Based Waveform Recommendation: A New Communication Waveform Design Paradigm","created":"2022-01-24","cited_by_count":0,"area":null},{"id":"2204.03842","title":"From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2204.12300","title":"Unified GCNs: Towards Connecting GCNs with CNNs","created":"2022-04-26","cited_by_count":0,"area":null},{"id":"2210.17141","title":"Studying inductive biases in image classification task","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2211.06163","title":"Dual Complementary Dynamic Convolution for Image Recognition","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2307.04995","title":"PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR","created":"2023-07-11","cited_by_count":0,"area":null},{"id":"2310.00342","title":"RBF Weighted Hyper-Involution for RGB-D Object Detection","created":"2023-09-30","cited_by_count":0,"area":null},{"id":"2310.00369","title":"LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression","created":"2023-09-30","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":"2401.14749","title":"Topology-Aware Exploration of Energy-Based Models Equilibrium: Toric QC-LDPC Codes and Hyperbolic MET QC-LDPC Codes","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2404.06593","title":"Spatially Optimized Compact Deep Metric Learning Model for Similarity Search","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2503.14779","title":"Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolution","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2503.15800","title":"Frequency Enhancement for Image Demosaicking","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2505.08233","title":"G-MSGINet: A Grouped Multi-Scale Graph-Involution Network for Contactless Fingerprint Recognition","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2507.11550","title":"Deformable Dynamic Convolution for Accurate yet Efficient Spatio-Temporal Traffic Prediction","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2508.06147","title":"DSConv: Dynamic Splitting Convolution for Pansharpening","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2510.20092","title":"Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.18422","title":"NeuroVascU-Net: A Unified Multi-Scale and Cross-Domain Adaptive Feature Fusion U-Net for Precise 3D Segmentation of Brain Vessels in Contrast-Enhanced T1 MRI","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.24463","title":"Spectral and Spatial Graph Learning for Multispectral Solar Image Compression","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2602.18965","title":"Face Presentation Attack Detection via Content-Adaptive Spatial Operators","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2602.23496","title":"SGDC: Structurally-Guided Dynamic Convolution for Medical Image Segmentation","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.12547","title":"Decoding Matters: Efficient Mamba-Based Decoder with Distribution-Aware Deep Supervision for Medical Image Segmentation","created":"2026-03-13","cited_by_count":0,"area":"ssm"},{"id":"2604.23320","title":"KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.01711","title":"Linear-Time Global Visual Modeling without Explicit Attention","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2608.11860","title":"Two-Stage Deformable-Convolutional Inverse Design of Nanophotonic Absorbers from Optical Spectra","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.19817","title":"Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.27282","title":"TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.01069","title":"Overcoming Kernel Redundancy for Scaling Logic Gate Networks","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}