{"total":260,"rows":[{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210,"area":null},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056,"area":"ssm"},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738,"area":null},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632,"area":null},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532,"area":null},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524,"area":null},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302,"area":null},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248,"area":null},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2205.08897","title":"FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting","created":"2022-05-18","cited_by_count":147,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"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":"2202.13556","title":"Filter-enhanced MLP is All You Need for Sequential Recommendation","created":"2022-02-28","cited_by_count":96,"area":null},{"id":"2209.04934","title":"Clifford Neural Layers for PDE Modeling","created":"2022-09-08","cited_by_count":92,"area":null},{"id":"2303.17472","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","created":"2023-03-30","cited_by_count":92,"area":null},{"id":"2403.15360","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","created":"2024-03-22","cited_by_count":82,"area":"ssm"},{"id":"2111.11745","title":"Intriguing Findings of Frequency Selection for Image Deblurring","created":"2021-11-23","cited_by_count":81,"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":"2304.10716","title":"Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers","created":"2023-04-21","cited_by_count":81,"area":"inference"},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78,"area":null},{"id":"2404.08472","title":"TSLANet: Rethinking Transformers for Time Series Representation Learning","created":"2024-04-12","cited_by_count":74,"area":null},{"id":"2407.05848","title":"Wavelet Convolutions for Large Receptive Fields","created":"2024-07-08","cited_by_count":74,"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":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61,"area":null},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58,"area":null},{"id":"2304.06446","title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","created":"2023-04-13","cited_by_count":48,"area":null},{"id":"2408.12879","title":"Frequency-aware Feature Fusion for Dense Image Prediction","created":"2024-08-23","cited_by_count":48,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"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":"2403.20035","title":"UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation","created":"2024-03-29","cited_by_count":45,"area":"ssm"},{"id":"2203.12198","title":"Deep Frequency Filtering for Domain Generalization","created":"2022-03-23","cited_by_count":43,"area":null},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43,"area":null},{"id":"2403.13642","title":"H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation","created":"2024-03-20","cited_by_count":35,"area":"ssm"},{"id":"2403.05369","title":"Frequency-Adaptive Dilated Convolution for Semantic Segmentation","created":"2024-03-08","cited_by_count":34,"area":null},{"id":"2108.13002","title":"A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP","created":"2021-08-30","cited_by_count":32,"area":null},{"id":"2301.11509","title":"Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation","created":"2023-01-27","cited_by_count":32,"area":null},{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"area":null},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30,"area":null},{"id":"2201.12083","title":"DynaMixer: A Vision MLP Architecture with Dynamic Mixing","created":"2022-01-28","cited_by_count":28,"area":null},{"id":"2303.11674","title":"ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization","created":"2023-03-21","cited_by_count":28,"area":null},{"id":"2203.09064","title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","created":"2022-03-17","cited_by_count":27,"area":null},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25,"area":null},{"id":"2108.01072","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2205.01972","title":"Sequencer: Deep LSTM for Image Classification","created":"2022-05-04","cited_by_count":23,"area":null},{"id":"2309.05927","title":"Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals","created":"2023-09-12","cited_by_count":23,"area":null},{"id":"2301.04648","title":"Head-Free Lightweight Semantic Segmentation with Linear Transformer","created":"2023-01-11","cited_by_count":22,"area":null},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22,"area":null},{"id":"2111.12527","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2308.10285","title":"DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization","created":"2023-08-20","cited_by_count":21,"area":null},{"id":"2407.16993","title":"LoFormer: Local Frequency Transformer for Image Deblurring","created":"2024-07-24","cited_by_count":20,"area":null},{"id":"2205.14375","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","created":"2022-05-28","cited_by_count":19,"area":null},{"id":"2303.13043","title":"Top-Down Visual Attention from Analysis by Synthesis","created":"2023-03-23","cited_by_count":19,"area":null},{"id":"2406.16531","title":"GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2503.18783","title":"Frequency Dynamic Convolution for Dense Image Prediction","created":"2025-03-24","cited_by_count":19,"area":null},{"id":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","cited_by_count":18,"area":null},{"id":"2401.04861","title":"CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video","created":"2024-01-10","cited_by_count":18,"area":null},{"id":"2408.07307","title":"Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery","created":"2024-08-14","cited_by_count":18,"area":null},{"id":"2409.13222","title":"3D-GSW: 3D Gaussian Splatting for Robust Watermarking","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2311.01310","title":"Scattering Vision Transformer: Spectral Mixing Matters","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2410.22135","title":"Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation","created":"2024-10-29","cited_by_count":17,"area":null},{"id":"2306.00451","title":"S$^2$ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation","created":"2023-06-01","cited_by_count":15,"area":null},{"id":"2308.11568","title":"SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation","created":"2023-08-22","cited_by_count":14,"area":null},{"id":"2407.17757","title":"CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions","created":"2024-07-25","cited_by_count":14,"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":"2211.11052","title":"Convexifying Transformers: Improving optimization and understanding of transformer networks","created":"2022-11-20","cited_by_count":12,"area":null},{"id":"2211.15362","title":"Exploring the Coordination of Frequency and Attention in Masked Image Modeling","created":"2022-11-28","cited_by_count":12,"area":null},{"id":"2304.10864","title":"FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation","created":"2023-04-21","cited_by_count":11,"area":null},{"id":"2312.04234","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","created":"2023-12-07","cited_by_count":11,"area":null},{"id":"2506.10962","title":"SpectralAR: Spectral Autoregressive Visual Generation","created":"2025-06-12","cited_by_count":11,"area":"diffusion"},{"id":"2207.01287","title":"FFCNet: Fourier Transform-Based Frequency Learning and Complex Convolutional Network for Colon Disease Classification","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2404.15174","title":"Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion","created":"2024-04-23","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":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","cited_by_count":9,"area":null},{"id":"2312.11023","title":"Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector","created":"2023-12-18","cited_by_count":9,"area":null},{"id":"2605.26501","title":"Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization","created":"2026-05-26","cited_by_count":9,"area":"mllm"},{"id":"2207.11678","title":"Quad-Net: Quad-domain Network for CT Metal Artifact Reduction","created":"2022-07-24","cited_by_count":8,"area":null},{"id":"2210.14007","title":"MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation","created":"2022-10-25","cited_by_count":8,"area":null},{"id":"2212.04689","title":"Non-equispaced Fourier Neural Solvers for PDEs","created":"2022-12-09","cited_by_count":8,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2307.10001","title":"As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2405.18679","title":"Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain","created":"2024-05-29","cited_by_count":8,"area":"ssm"},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2211.08252","title":"Dynamic Temporal Filtering in Video Models","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2304.01227","title":"Resolution-Invariant Image Classification based on Fourier Neural Operators","created":"2023-04-02","cited_by_count":7,"area":null},{"id":"2405.16555","title":"Building Vision Models upon Heat Conduction","created":"2024-05-26","cited_by_count":7,"area":null},{"id":"2508.11330","title":"Noise Matters: Optimizing Matching Noise for Diffusion Classifiers","created":"2025-08-15","cited_by_count":7,"area":"mllm"},{"id":"2202.06510","title":"Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs","created":"2022-02-14","cited_by_count":6,"area":null},{"id":"2301.07330","title":"FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment","created":"2023-01-18","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":"2312.03781","title":"Lite-Mind: Towards Efficient and Robust Brain Representation Network","created":"2023-12-06","cited_by_count":6,"area":null},{"id":"2402.05830","title":"Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting","created":"2024-02-08","cited_by_count":6,"area":null},{"id":"2406.01460","title":"MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2406.07435","title":"Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration","created":"2024-06-11","cited_by_count":6,"area":null}],"next_cursor":"100"}