{"total":496,"rows":[{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940,"area":null},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"area":null},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738,"area":null},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435,"area":null},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330,"area":null},{"id":"2107.12571","title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","created":"2021-07-27","cited_by_count":321,"area":null},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216,"area":null},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"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":"2109.03201","title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","created":"2021-09-07","cited_by_count":180,"area":null},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167,"area":null},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158,"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":"2104.04314","title":"CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching","created":"2021-04-09","cited_by_count":154,"area":null},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149,"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":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","cited_by_count":125,"area":null},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123,"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":"2205.09753","title":"HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding","created":"2022-04-30","cited_by_count":110,"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":"2207.14191","title":"Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation","created":"2022-07-28","cited_by_count":76,"area":null},{"id":"2407.05848","title":"Wavelet Convolutions for Large Receptive Fields","created":"2024-07-08","cited_by_count":74,"area":null},{"id":"2104.07660","title":"SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements","created":"2021-04-15","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":"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":"2311.17132","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2107.05274","title":"TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation","created":"2021-07-12","cited_by_count":60,"area":null},{"id":"2304.07213","title":"Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar","created":"2023-04-14","cited_by_count":60,"area":null},{"id":"2101.09864","title":"Applications of Deep Learning in Fundus Images: A Review","created":"2021-01-25","cited_by_count":59,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2112.01530","title":"StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions","created":"2021-12-02","cited_by_count":58,"area":null},{"id":"2201.07436","title":"Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth","created":"2022-01-19","cited_by_count":58,"area":null},{"id":"2105.09511","title":"Medical Image Segmentation Using Squeeze-and-Expansion Transformers","created":"2021-05-20","cited_by_count":57,"area":null},{"id":"2201.09206","title":"A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization","created":"2022-01-23","cited_by_count":57,"area":null},{"id":"2205.14623","title":"SKFlow: Learning Optical Flow with Super Kernels","created":"2022-05-29","cited_by_count":56,"area":null},{"id":"2307.15615","title":"A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond","created":"2023-07-28","cited_by_count":55,"area":null},{"id":"2307.08093","title":"Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collections","created":"2023-07-16","cited_by_count":54,"area":null},{"id":"2105.14217","title":"Less is More: Pay Less Attention in Vision Transformers","created":"2021-05-29","cited_by_count":53,"area":null},{"id":"2104.04386","title":"Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding","created":"2021-04-09","cited_by_count":52,"area":null},{"id":"2201.09376","title":"ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer","created":"2022-01-23","cited_by_count":52,"area":null},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51,"area":null},{"id":"2302.12721","title":"LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version","created":"2023-02-24","cited_by_count":50,"area":null},{"id":"2203.11947","title":"CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training","created":"2022-03-22","cited_by_count":49,"area":null},{"id":"2405.16105","title":"MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space","created":"2024-05-25","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":"2307.14863","title":"IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer","created":"2023-07-27","cited_by_count":44,"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":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44,"area":null},{"id":"2103.14470","title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","created":"2021-03-26","cited_by_count":43,"area":null},{"id":"2409.17920","title":"Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation","created":"2024-09-26","cited_by_count":43,"area":null},{"id":"2104.11408","title":"Neural Mean Discrepancy for Efficient Out-of-Distribution Detection","created":"2021-04-23","cited_by_count":42,"area":null},{"id":"2212.10356","title":"Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2202.06988","title":"Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons","created":"2022-02-14","cited_by_count":39,"area":null},{"id":"2106.02994","title":"Learning Topology from Synthetic Data for Unsupervised Depth Completion","created":"2021-06-06","cited_by_count":38,"area":null},{"id":"2106.03714","title":"Refiner: Refining Self-attention for Vision Transformers","created":"2021-06-07","cited_by_count":38,"area":null},{"id":"2212.05946","title":"Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks","created":"2022-12-12","cited_by_count":37,"area":null},{"id":"2307.14071","title":"Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching","created":"2023-07-26","cited_by_count":37,"area":null},{"id":"2209.09475","title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","created":"2022-09-20","cited_by_count":36,"area":null},{"id":"2407.11087","title":"Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV","created":"2024-07-14","cited_by_count":36,"area":null},{"id":"2206.10177","title":"TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks","created":"2022-06-21","cited_by_count":35,"area":null},{"id":"2208.03364","title":"GLASS: Global to Local Attention for Scene-Text Spotting","created":"2022-08-05","cited_by_count":34,"area":null},{"id":"2304.00424","title":"Progressive Random Convolutions for Single Domain Generalization","created":"2023-04-02","cited_by_count":34,"area":null},{"id":"2412.16986","title":"Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection","created":"2024-12-22","cited_by_count":34,"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":"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":"2303.05506","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","created":"2023-03-09","cited_by_count":32,"area":null},{"id":"2308.09891","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","created":"2023-08-19","cited_by_count":32,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2205.10435","title":"Towards Better Understanding Attribution Methods","created":"2022-05-20","cited_by_count":28,"area":null},{"id":"2106.03412","title":"Resolution learning in deep convolutional networks using scale-space theory","created":"2021-06-07","cited_by_count":26,"area":null},{"id":"2201.02526","title":"Learning Target-aware Representation for Visual Tracking via Informative Interactions","created":"2022-01-07","cited_by_count":25,"area":null},{"id":"2303.14348","title":"Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style","created":"2023-03-25","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":"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":"2106.04108","title":"Fully Transformer Networks for Semantic Image Segmentation","created":"2021-06-08","cited_by_count":24,"area":null},{"id":"2103.17220","title":"Scale-aware Automatic Augmentation for Object Detection","created":"2021-03-31","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":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23,"area":null},{"id":"2112.03423","title":"Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision","created":"2021-12-06","cited_by_count":22,"area":null},{"id":"2204.13630","title":"Rotationally Equivariant 3D Object Detection","created":"2022-04-28","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":"2507.19125","title":"Learned Image Compression with Hierarchical Progressive Context Modeling","created":"2025-07-25","cited_by_count":21,"area":null},{"id":"2112.03740","title":"Dilated convolution with learnable spacings","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2404.16573","title":"Multi-Scale Representations by Varying Window Attention for Semantic Segmentation","created":"2024-04-25","cited_by_count":20,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2104.10127","title":"Generative Transformer for Accurate and Reliable Salient Object Detection","created":"2021-04-20","cited_by_count":18,"area":null},{"id":"2106.02599","title":"SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networks","created":"2021-06-04","cited_by_count":18,"area":null},{"id":"2108.13576","title":"Dead Pixel Test Using Effective Receptive Field","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2212.04673","title":"MSI: Maximize Support-Set Information for Few-Shot Segmentation","created":"2022-12-09","cited_by_count":18,"area":null},{"id":"2309.14531","title":"Pixel-Grounded Prototypical Part Networks","created":"2023-09-25","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":"2412.03177","title":"PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation","created":"2024-12-04","cited_by_count":18,"area":null},{"id":"2105.12395","title":"Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks","created":"2021-05-26","cited_by_count":17,"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":"2412.08774","title":"ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder","created":"2024-12-11","cited_by_count":17,"area":null}],"next_cursor":"100"}