{"total":201,"rows":[{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"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":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117,"area":null},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117,"area":null},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113,"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":"2301.03580","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","created":"2023-01-09","cited_by_count":94,"area":null},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86,"area":null},{"id":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86,"area":null},{"id":"2211.11943","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78,"area":null},{"id":"2407.05848","title":"Wavelet Convolutions for Large Receptive Fields","created":"2024-07-08","cited_by_count":74,"area":null},{"id":"2204.11716","title":"Masked Image Modeling Advances 3D Medical Image Analysis","created":"2022-04-25","cited_by_count":72,"area":null},{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68,"area":null},{"id":"2309.09668","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","created":"2023-09-18","cited_by_count":60,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2302.13800","title":"Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution","created":"2023-02-27","cited_by_count":57,"area":null},{"id":"2403.19967","title":"Rewrite the Stars","created":"2024-03-29","cited_by_count":55,"area":null},{"id":"2306.11249","title":"OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning","created":"2023-06-20","cited_by_count":54,"area":null},{"id":"2403.06258","title":"Poly Kernel Inception Network for Remote Sensing Detection","created":"2024-03-10","cited_by_count":52,"area":null},{"id":"2307.08579","title":"Scale-Aware Modulation Meet Transformer","created":"2023-07-17","cited_by_count":49,"area":null},{"id":"2403.06534","title":"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection","created":"2024-03-11","cited_by_count":48,"area":null},{"id":"2412.13443","title":"DarkIR: Robust Low-Light Image Restoration","created":"2024-12-18","cited_by_count":48,"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":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43,"area":null},{"id":"2205.05675","title":"NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results","created":"2022-05-11","cited_by_count":40,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31,"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":"2309.00121","title":"Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation","created":"2023-08-31","cited_by_count":30,"area":null},{"id":"2209.14145","title":"Multi-scale Attention Network for Single Image Super-Resolution","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2206.09325","title":"EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm","created":"2022-06-19","cited_by_count":27,"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":"2405.09365","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","created":"2024-05-15","cited_by_count":25,"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":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2305.08824","title":"Five A$^{+}$ Network: You Only Need 9K Parameters for Underwater Image Enhancement","created":"2023-05-15","cited_by_count":22,"area":null},{"id":"2403.18383","title":"Generative Multi-modal Models are Good Class-Incremental Learners","created":"2024-03-27","cited_by_count":22,"area":null},{"id":"2412.20665","title":"SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection","created":"2024-12-30","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":"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":"2305.17654","title":"MixDehazeNet : Mix Structure Block For Image Dehazing Network","created":"2023-05-28","cited_by_count":18,"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":"2403.19963","title":"Efficient Modulation for Vision Networks","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2303.02885","title":"Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints","created":"2023-03-06","cited_by_count":15,"area":null},{"id":"2302.11416","title":"Structure Embedded Nucleus Classification for Histopathology Images","created":"2023-02-22","cited_by_count":14,"area":null},{"id":"2412.18459","title":"Underwater Image Restoration via Polymorphic Large Kernel CNNs","created":"2024-12-24","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":"2401.05633","title":"Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2405.15365","title":"U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2308.09564","title":"Deep Equilibrium Object Detection","created":"2023-08-18","cited_by_count":10,"area":null},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","cited_by_count":10,"area":null},{"id":"2210.06747","title":"DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2407.14340","title":"Large Kernel Distillation Network for Efficient Single Image Super-Resolution","created":"2024-07-19","cited_by_count":9,"area":null},{"id":"2411.15678","title":"Towards RAW Object Detection in Diverse Conditions","created":"2024-11-24","cited_by_count":9,"area":null},{"id":"2205.08780","title":"Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving","created":"2022-05-18","cited_by_count":8,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"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":"2211.07198","title":"Fcaformer: Forward Cross Attention in Hybrid Vision Transformer","created":"2022-11-14","cited_by_count":7,"area":null},{"id":"2303.11637","title":"Equiangular Basis Vectors","created":"2023-03-21","cited_by_count":7,"area":null},{"id":"2403.13395","title":"Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments","created":"2024-03-20","cited_by_count":7,"area":null},{"id":"2208.07039","title":"Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning","created":"2022-08-15","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":"2405.13335","title":"Vision Transformer with Sparse Scan Prior","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2204.09213","title":"Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network","created":"2022-04-20","cited_by_count":5,"area":null},{"id":"2210.06455","title":"Token-Label Alignment for Vision Transformers","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2212.02952","title":"Simple Baseline for Weather Forecasting Using Spatiotemporal Context Aggregation Network","created":"2022-12-06","cited_by_count":5,"area":null},{"id":"2212.10049","title":"OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2302.00722","title":"A Survey of Deep Learning: From Activations to Transformers","created":"2023-02-01","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":"2305.17337","title":"Benchmarking Diverse-Modal Entity Linking with Generative Models","created":"2023-05-27","cited_by_count":5,"area":null},{"id":"2306.07656","title":"Is Anisotropy Inherent to Transformers?","created":"2023-06-13","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":"2308.12494","title":"MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2309.00143","title":"Self-supervised Semantic Segmentation: Consistency over Transformation","created":"2023-08-31","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":"2401.11734","title":"Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey","created":"2024-01-22","cited_by_count":5,"area":null},{"id":"2403.18637","title":"Transformers-based architectures for stroke segmentation: A review","created":"2024-03-27","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":"2505.18423","title":"CENet: Context Enhancement Network for Medical Image Segmentation","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2211.06816","title":"Long-Range Zero-Shot Generative Deep Network Quantization","created":"2022-11-13","cited_by_count":4,"area":null},{"id":"2305.17644","title":"Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation","created":"2023-05-28","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":"2401.12736","title":"$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect","created":"2024-01-23","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":"2412.02054","title":"Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunable","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2209.08816","title":"LGC-Net: A Lightweight Gyroscope Calibration Network for Efficient Attitude Estimation","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2212.04005","title":"RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts","created":"2022-12-07","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":"2312.09743","title":"SLS4D: Sparse Latent Space for 4D Novel View Synthesis","created":"2023-12-15","cited_by_count":3,"area":null},{"id":"2403.17177","title":"Deep models for stroke segmentation: do complex architectures always perform better?","created":"2024-03-25","cited_by_count":3,"area":null}],"next_cursor":"100"}