{"total":121,"rows":[{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"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":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"area":null},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","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":"2306.09364","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":139,"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":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117,"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":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72,"area":null},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66,"area":null},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"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":"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":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46,"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":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43,"area":null},{"id":"2202.12165","title":"Transformers in Medical Image Analysis: A Review","created":"2022-02-24","cited_by_count":41,"area":null},{"id":"2210.16721","title":"Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction","created":"2022-10-30","cited_by_count":39,"area":null},{"id":"2109.04454","title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","created":"2021-09-09","cited_by_count":37,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2207.13159","title":"TINYCD: A (Not So) Deep Learning Model For Change Detection","created":"2022-07-26","cited_by_count":36,"area":null},{"id":"2307.00395","title":"MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications","created":"2023-07-01","cited_by_count":35,"area":null},{"id":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"area":null},{"id":"2112.11081","title":"RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality","created":"2021-12-21","cited_by_count":32,"area":null},{"id":"2201.10801","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","created":"2022-01-26","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":"2108.01072","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2112.04863","title":"3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis","created":"2021-12-09","cited_by_count":23,"area":null},{"id":"2205.01972","title":"Sequencer: Deep LSTM for Image Classification","created":"2022-05-04","cited_by_count":23,"area":null},{"id":"2110.01775","title":"Deep Instance Segmentation with Automotive Radar Detection Points","created":"2021-10-05","cited_by_count":22,"area":null},{"id":"2309.13363","title":"MLPST: MLP is All You Need for Spatio-Temporal Prediction","created":"2023-09-23","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":"2205.10528","title":"PointVector: A Vector Representation In Point Cloud Analysis","created":"2022-05-21","cited_by_count":21,"area":null},{"id":"2206.06420","title":"GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation","created":"2022-06-13","cited_by_count":21,"area":null},{"id":"2203.03990","title":"Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs","created":"2022-03-08","cited_by_count":20,"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":"2203.14679","title":"Brain-inspired Multilayer Perceptron with Spiking Neurons","created":"2022-03-28","cited_by_count":16,"area":null},{"id":"2304.13700","title":"UniNeXt: Exploring A Unified Architecture for Vision Recognition","created":"2023-04-26","cited_by_count":16,"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":"2410.17241","title":"Frontiers in Intelligent Colonoscopy","created":"2024-10-22","cited_by_count":14,"area":null},{"id":"2207.05366","title":"Image and Model Transformation with Secret Key for Vision Transformer","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2307.11458","title":"Strip-MLP: Efficient Token Interaction for Vision MLP","created":"2023-07-21","cited_by_count":12,"area":null},{"id":"2401.17992","title":"Multilinear Operator Networks","created":"2024-01-31","cited_by_count":12,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2407.11321","title":"TCFormer: Visual Recognition via Token Clustering Transformer","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2210.00132","title":"Alignment-guided Temporal Attention for Video Action Recognition","created":"2022-09-30","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":"2202.02018","title":"Image-to-Image MLP-mixer for Image Reconstruction","created":"2022-02-04","cited_by_count":9,"area":null},{"id":"2206.06292","title":"MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing","created":"2022-06-13","cited_by_count":9,"area":null},{"id":"2203.08219","title":"CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP","created":"2022-03-15","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":"2407.13108","title":"UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2305.14758","title":"MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2306.14525","title":"ParameterNet: Parameters Are All You Need","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"area":null},{"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":"2203.06108","title":"Active Token Mixer","created":"2022-03-11","cited_by_count":6,"area":null},{"id":"2203.10395","title":"Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning","created":"2022-03-19","cited_by_count":6,"area":null},{"id":"2208.13138","title":"ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers","created":"2022-08-28","cited_by_count":6,"area":null},{"id":"2209.01404","title":"Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies","created":"2022-09-03","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":"2311.16707","title":"Full-resolution MLPs Empower Medical Dense Prediction","created":"2023-11-28","cited_by_count":6,"area":null},{"id":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2108.04384","title":"RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2108.07007","title":"Flying Guide Dog: Walkable Path Discovery for the Visually Impaired Utilizing Drones and Transformer-based Semantic Segmentation","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2208.11718","title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","created":"2022-08-24","cited_by_count":5,"area":null},{"id":"2305.18281","title":"HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition","created":"2023-05-29","cited_by_count":5,"area":null},{"id":"2308.04206","title":"Exploring Transformers for Open-world Instance Segmentation","created":"2023-08-08","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":"2502.09928","title":"Deep Tree Tensor Networks","created":"2025-02-14","cited_by_count":5,"area":null},{"id":"2111.13156","title":"Global Interaction Modelling in Vision Transformer via Super Tokens","created":"2021-11-25","cited_by_count":4,"area":null},{"id":"2111.13677","title":"SWAT: Spatial Structure Within and Among Tokens","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2203.12893","title":"FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2305.00671","title":"PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation","created":"2023-05-01","cited_by_count":4,"area":null},{"id":"2507.09446","title":"Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions","created":"2025-07-13","cited_by_count":4,"area":null},{"id":"2201.00978","title":"PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2212.14158","title":"BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2303.13111","title":"Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2202.10240","title":"Rethinking the Zigzag Flattening for Image Reading","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2204.06779","title":"3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2205.14477","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","created":"2022-05-28","cited_by_count":2,"area":null},{"id":"2208.10701","title":"CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Image","created":"2022-08-23","cited_by_count":2,"area":null},{"id":"2302.00885","title":"AOP-Net: All-in-One Perception Network for Joint LiDAR-based 3D Object Detection and Panoptic Segmentation","created":"2023-02-02","cited_by_count":2,"area":null},{"id":"2309.01620","title":"Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2402.02377","title":"NOAH: Learning Pairwise Object Category Attentions for Image Classification","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.04394","title":"SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2207.07284","title":"Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2208.11108","title":"Efficient Attention-free Video Shift Transformers","created":"2022-08-23","cited_by_count":1,"area":null},{"id":"2301.08868","title":"Computationally Efficient 3D MRI Reconstruction with Adaptive MLP","created":"2023-01-21","cited_by_count":1,"area":null},{"id":"2304.03532","title":"Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction","created":"2023-04-07","cited_by_count":1,"area":null},{"id":"2304.08803","title":"MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition","created":"2023-04-18","cited_by_count":1,"area":null}],"next_cursor":"100"}