{"total":155,"rows":[{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"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":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130,"area":null},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117,"area":null},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105,"area":null},{"id":"2207.14284","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","created":"2022-07-28","cited_by_count":103,"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":"2209.15076","title":"3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation","created":"2022-09-29","cited_by_count":94,"area":null},{"id":"2301.03580","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","created":"2023-01-09","cited_by_count":94,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2302.08106","title":"Towards Efficient Visual Adaption via Structural Re-parameterization","created":"2023-02-16","cited_by_count":73,"area":null},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72,"area":null},{"id":"2206.10810","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","created":"2022-06-22","cited_by_count":68,"area":null},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65,"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":"2311.17132","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2411.16061","title":"Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training","created":"2024-11-25","cited_by_count":59,"area":null},{"id":"2205.15175","title":"ShuffleMixer: An Efficient ConvNet for Image Super-Resolution","created":"2022-05-30","cited_by_count":45,"area":null},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43,"area":null},{"id":"2205.14756","title":"EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction","created":"2022-05-29","cited_by_count":42,"area":null},{"id":"2208.04939","title":"U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?","created":"2022-08-07","cited_by_count":40,"area":null},{"id":"2206.03452","title":"Can CNNs Be More Robust Than Transformers?","created":"2022-06-07","cited_by_count":38,"area":null},{"id":"2304.04237","title":"Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention","created":"2023-04-09","cited_by_count":38,"area":null},{"id":"2206.14383","title":"Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems","created":"2022-06-29","cited_by_count":37,"area":null},{"id":"2205.15242","title":"Re-parameterizing Your Optimizers rather than Architectures","created":"2022-05-30","cited_by_count":35,"area":null},{"id":"2302.06492","title":"Optical flow estimation from event-based cameras and spiking neural networks","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2212.11005","title":"Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective","created":"2022-12-21","cited_by_count":28,"area":null},{"id":"2303.16094","title":"LinK: Linear Kernel for LiDAR-based 3D Perception","created":"2023-03-28","cited_by_count":26,"area":null},{"id":"2306.00396","title":"Lightweight Vision Transformer with Bidirectional Interaction","created":"2023-06-01","cited_by_count":25,"area":null},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25,"area":null},{"id":"2205.01972","title":"Sequencer: Deep LSTM for Image Classification","created":"2022-05-04","cited_by_count":23,"area":null},{"id":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2210.05950","title":"ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors","created":"2022-10-12","cited_by_count":21,"area":null},{"id":"2309.01430","title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","created":"2023-09-04","cited_by_count":21,"area":null},{"id":"2310.19380","title":"TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition","created":"2023-10-30","cited_by_count":21,"area":null},{"id":"2210.15491","title":"GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer","created":"2022-10-27","cited_by_count":18,"area":null},{"id":"2305.00603","title":"Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation","created":"2023-04-30","cited_by_count":18,"area":null},{"id":"2305.17654","title":"MixDehazeNet : Mix Structure Block For Image Dehazing Network","created":"2023-05-28","cited_by_count":18,"area":null},{"id":"2311.15607","title":"Spatially Covariant Image Registration with Text Prompts","created":"2023-11-27","cited_by_count":18,"area":null},{"id":"2211.05296","title":"Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2210.05960","title":"Efficient Image Super-Resolution using Vast-Receptive-Field Attention","created":"2022-10-12","cited_by_count":16,"area":null},{"id":"2303.02165","title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","created":"2023-03-05","cited_by_count":14,"area":null},{"id":"2308.10481","title":"ADNet: Lane Shape Prediction via Anchor Decomposition","created":"2023-08-21","cited_by_count":14,"area":null},{"id":"2501.03775","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","created":"2025-01-07","cited_by_count":14,"area":null},{"id":"2209.01788","title":"LKD-Net: Large Kernel Convolution Network for Single Image Dehazing","created":"2022-09-05","cited_by_count":13,"area":null},{"id":"2304.05659","title":"RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer","created":"2023-04-12","cited_by_count":13,"area":null},{"id":"2401.05633","title":"Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2209.11448","title":"Rethinking Performance Gains in Image Dehazing Networks","created":"2022-09-23","cited_by_count":12,"area":null},{"id":"2303.05785","title":"Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation","created":"2023-03-10","cited_by_count":12,"area":null},{"id":"2305.06568","title":"Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation","created":"2023-05-11","cited_by_count":12,"area":null},{"id":"2205.09579","title":"TRT-ViT: TensorRT-oriented Vision Transformer","created":"2022-05-19","cited_by_count":10,"area":null},{"id":"2308.00574","title":"PVG: Progressive Vision Graph for Vision Recognition","created":"2023-08-01","cited_by_count":10,"area":null},{"id":"2212.07623","title":"SBSS: Stacking-Based Semantic Segmentation Framework for Very High Resolution Remote Sensing Image","created":"2022-12-15","cited_by_count":9,"area":null},{"id":"2302.02234","title":"Revisiting Image Deblurring with an Efficient ConvNet","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2304.11805","title":"OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2211.05781","title":"Demystify Transformers & Convolutions in Modern Image Deep Networks","created":"2022-11-10","cited_by_count":7,"area":null},{"id":"2407.13538","title":"EnergyDiff: Universal Time-Series Energy Data Generation using Diffusion Models","created":"2024-07-18","cited_by_count":7,"area":"diffusion"},{"id":"2304.02330","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2305.02507","title":"Stimulative Training++: Go Beyond The Performance Limits of Residual Networks","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2306.06365","title":"FalconNet: Factorization for the Light-weight ConvNets","created":"2023-06-10","cited_by_count":6,"area":null},{"id":"2307.16140","title":"Fully $1\\times1$ Convolutional Network for Lightweight Image Super-Resolution","created":"2023-07-30","cited_by_count":6,"area":null},{"id":"2312.10588","title":"Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting","created":"2023-12-17","cited_by_count":6,"area":null},{"id":"2401.09833","title":"Slicer Networks","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2301.06719","title":"FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs","created":"2023-01-17","cited_by_count":5,"area":null},{"id":"2302.03861","title":"SwinCross: Cross-modal Swin Transformer for Head-and-Neck Tumor Segmentation in PET/CT Images","created":"2023-02-08","cited_by_count":5,"area":null},{"id":"2308.07251","title":"Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2310.00199","title":"DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable Convolution","created":"2023-09-30","cited_by_count":5,"area":null},{"id":"2312.08614","title":"Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Cost","created":"2023-12-14","cited_by_count":5,"area":null},{"id":"2411.16170","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2411.17214","title":"MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution","created":"2024-11-26","cited_by_count":5,"area":null},{"id":"2207.13560","title":"D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing","created":"2022-07-27","cited_by_count":4,"area":null},{"id":"2211.00859","title":"Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in The Dark","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2301.11360","title":"The Power of Linear Combinations: Learning with Random Convolutions","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2305.14039","title":"Learning a Single Convolutional Layer Model for Low Light Image Enhancement","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2306.00817","title":"Dilated Convolution with Learnable Spacings: beyond bilinear interpolation","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2404.12210","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2501.07806","title":"Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation","created":"2025-01-14","cited_by_count":4,"area":null},{"id":"2507.04118","title":"PromptSR: Cascade Prompting for Lightweight Image Super-Resolution","created":"2025-07-05","cited_by_count":4,"area":null},{"id":"2209.10907","title":"DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching","created":"2022-09-22","cited_by_count":3,"area":null},{"id":"2212.12552","title":"A Close Look at Spatial Modeling: From Attention to Convolution","created":"2022-12-23","cited_by_count":3,"area":null},{"id":"2306.09939","title":"Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2306.10265","title":"NBMOD: Find It and Grasp It in Noisy Background","created":"2023-06-17","cited_by_count":3,"area":null},{"id":"2307.11862","title":"Digital Modeling on Large Kernel Metamaterial Neural Network","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2312.13066","title":"PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2409.08510","title":"CasDyF-Net: Image Dehazing via Cascaded Dynamic Filters","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2504.02440","title":"HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2508.16881","title":"AWM-Fuse: Multi-Modality Image Fusion for Adverse Weather via Global and Local Text Perception","created":"2025-08-23","cited_by_count":3,"area":null},{"id":"2211.07398","title":"Age Prediction Performance Varies Across Deep, Superficial, and Cerebellar White Matter Connections","created":"2022-11-11","cited_by_count":2,"area":null},{"id":"2212.02248","title":"Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects","created":"2022-12-02","cited_by_count":2,"area":null},{"id":"2212.08490","title":"LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2301.10208","title":"A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2303.02131","title":"Spacetime-Efficient Low-Depth Quantum State Preparation with Applications","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2303.14324","title":"Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution","created":"2023-03-25","cited_by_count":2,"area":null}],"next_cursor":"100"}