{"total":172,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"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":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184,"area":null},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751,"area":null},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555,"area":null},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471,"area":null},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340,"area":"diffusion"},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333,"area":null},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310,"area":null},{"id":"2204.03883","title":"Vision Transformers for Single Image Dehazing","created":"2022-04-08","cited_by_count":260,"area":null},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2105.14576","title":"StyTr$^2$: Image Style Transfer with Transformers","created":"2021-05-30","cited_by_count":187,"area":null},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184,"area":null},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152,"area":null},{"id":"2207.09603","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","created":"2022-07-20","cited_by_count":137,"area":null},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2109.07162","title":"MISSFormer: An Effective Medical Image Segmentation Transformer","created":"2021-09-15","cited_by_count":103,"area":null},{"id":"2205.09671","title":"A graph-transformer for whole slide image classification","created":"2022-05-19","cited_by_count":84,"area":null},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83,"area":null},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79,"area":null},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78,"area":null},{"id":"2405.06880","title":"EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation","created":"2024-05-11","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":"2307.15421","title":"MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression","created":"2023-07-28","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":"2208.02541","title":"MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth","created":"2022-08-04","cited_by_count":53,"area":null},{"id":"2401.11673","title":"MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo","created":"2024-01-22","cited_by_count":50,"area":null},{"id":"2303.02584","title":"Super-Resolution Neural Operator","created":"2023-03-05","cited_by_count":49,"area":null},{"id":"2207.13686","title":"Shift-tolerant Perceptual Similarity Metric","created":"2022-07-27","cited_by_count":44,"area":null},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42,"area":null},{"id":"2406.17998","title":"Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model","created":"2024-06-26","cited_by_count":37,"area":null},{"id":"2203.10790","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","created":"2022-03-21","cited_by_count":36,"area":null},{"id":"2106.15947","title":"SOLO: A Simple Framework for Instance Segmentation","created":"2021-06-30","cited_by_count":32,"area":null},{"id":"2103.07362","title":"PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss","created":"2021-03-12","cited_by_count":31,"area":null},{"id":"2404.10156","title":"SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation","created":"2024-04-15","cited_by_count":31,"area":null},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2203.14333","title":"Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning","created":"2022-03-27","cited_by_count":26,"area":null},{"id":"2409.08573","title":"HTR-VT: Handwritten Text Recognition with Vision Transformer","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23,"area":null},{"id":"2203.11105","title":"High-fidelity GAN Inversion with Padding Space","created":"2022-03-21","cited_by_count":23,"area":null},{"id":"2405.11905","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","created":"2024-05-20","cited_by_count":23,"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":"2302.09818","title":"FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification","created":"2023-02-20","cited_by_count":21,"area":null},{"id":"2310.16175","title":"G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation","created":"2023-10-24","cited_by_count":21,"area":null},{"id":"2405.06849","title":"GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2204.11448","title":"High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation","created":"2022-04-25","cited_by_count":20,"area":null},{"id":"2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","created":"2021-12-02","cited_by_count":19,"area":null},{"id":"2104.06031","title":"Global Transport for Fluid Reconstruction with Learned Self-Supervision","created":"2021-04-13","cited_by_count":18,"area":null},{"id":"2305.10006","title":"EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging","created":"2023-05-17","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":"2104.05858","title":"Exploring Geometric Consistency for Monocular 3D Object Detection","created":"2021-04-12","cited_by_count":17,"area":null},{"id":"2108.01285","title":"Toward Spatially Unbiased Generative Models","created":"2021-08-03","cited_by_count":17,"area":null},{"id":"2205.03650","title":"Distilling Inter-Class Distance for Semantic Segmentation","created":"2022-05-07","cited_by_count":16,"area":"distill"},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2106.11160","title":"Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics","created":"2021-06-21","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":"2111.09499","title":"Dynamically pruning segformer for efficient semantic segmentation","created":"2021-11-18","cited_by_count":13,"area":null},{"id":"2409.00230","title":"Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observations","created":"2024-08-30","cited_by_count":13,"area":"diffusion"},{"id":"2108.07884","title":"Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs","created":"2021-08-17","cited_by_count":12,"area":null},{"id":"2204.08563","title":"Cylin-Painting: Seamless {360\\textdegree} Panoramic Image Outpainting and Beyond","created":"2022-04-18","cited_by_count":12,"area":null},{"id":"2107.12600","title":"PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution","created":"2021-07-27","cited_by_count":11,"area":null},{"id":"2110.02891","title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","created":"2021-10-06","cited_by_count":11,"area":null},{"id":"2112.04674","title":"DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2203.11987","title":"PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","cited_by_count":11,"area":null},{"id":"2301.07895","title":"Spatially Covariant Lesion Segmentation","created":"2023-01-19","cited_by_count":10,"area":null},{"id":"2312.09041","title":"Graph Neural Networks with Diverse Spectral Filtering","created":"2023-12-14","cited_by_count":9,"area":null},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2206.10075","title":"Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation","created":"2022-06-21","cited_by_count":8,"area":null},{"id":"2301.01661","title":"RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning","created":"2023-01-04","cited_by_count":8,"area":null},{"id":"2310.02674","title":"ObjFormer: Learning Land-Cover Changes From Paired OSM Data and Optical High-Resolution Imagery via Object-Guided Transformer","created":"2023-10-04","cited_by_count":8,"area":null},{"id":"2312.05771","title":"Hacking Task Confounder in Meta-Learning","created":"2023-12-10","cited_by_count":8,"area":null},{"id":"2411.15737","title":"TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models","created":"2024-11-24","cited_by_count":8,"area":null},{"id":"2107.12762","title":"Multi-Scale Local-Temporal Similarity Fusion for Continuous Sign Language Recognition","created":"2021-07-27","cited_by_count":7,"area":null},{"id":"2112.01767","title":"MT-TransUNet: Mediating Multi-Task Tokens in Transformers for Skin Lesion Segmentation and Classification","created":"2021-12-03","cited_by_count":7,"area":null},{"id":"2112.08001","title":"Autoencoder-based background reconstruction and foreground segmentation with background noise estimation","created":"2021-12-15","cited_by_count":7,"area":null},{"id":"2201.04906","title":"Hand-Object Interaction Reasoning","created":"2022-01-13","cited_by_count":7,"area":null},{"id":"2207.10023","title":"Tailoring Self-Supervision for Supervised Learning","created":"2022-07-20","cited_by_count":7,"area":null},{"id":"2306.16661","title":"NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency","created":"2023-06-29","cited_by_count":7,"area":null},{"id":"2407.07295","title":"Deformation-Recovery Diffusion Model (DRDM): Instance Deformation for Image Manipulation and Synthesis","created":"2024-07-10","cited_by_count":7,"area":"diffusion"},{"id":"2601.16192","title":"360Anything: Geometry-Free Lifting of Images and Videos to 360{\\deg}","created":"2026-01-22","cited_by_count":7,"area":null},{"id":"2105.05838","title":"Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning","created":"2021-05-12","cited_by_count":6,"area":null},{"id":"2207.08319","title":"Defect Transformer: An Efficient Hybrid Transformer Architecture for Surface Defect Detection","created":"2022-07-17","cited_by_count":6,"area":null},{"id":"2301.04608","title":"Padding Module: Learning the Padding in Deep Neural Networks","created":"2023-01-11","cited_by_count":6,"area":null},{"id":"2305.11474","title":"Reciprocal Attention Mixing Transformer for Lightweight Image Restoration","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2404.10841","title":"Gasformer: A Transformer-based Architecture for Segmenting Methane Emissions from Livestock in Optical Gas Imaging","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2503.05546","title":"Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2103.04020","title":"NeRD: Neural Representation of Distribution for Medical Image Segmentation","created":"2021-03-06","cited_by_count":5,"area":null},{"id":"2103.15812","title":"LatentKeypointGAN: Controlling Images via Latent Keypoints","created":"2021-03-29","cited_by_count":5,"area":null},{"id":"2204.12143","title":"Deeper Insights into the Robustness of ViTs towards Common Corruptions","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2305.15773","title":"Multi-scale Efficient Graph-Transformer for Whole Slide Image Classification","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2306.06579","title":"Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder","created":"2023-06-11","cited_by_count":5,"area":null},{"id":"2406.16012","title":"Wound Tissue Segmentation in Diabetic Foot Ulcer Images Using Deep Learning: A Pilot Study","created":"2024-06-23","cited_by_count":5,"area":null},{"id":"2410.17377","title":"PtychoFormer: A Transformer-based Model for Ptychographic Phase Retrieval","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2312.02136","title":"BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2402.00240","title":"Spectral Norm of Convolutional Layers with Circular and Zero Paddings","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2501.10967","title":"Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding","created":"2025-01-19","cited_by_count":4,"area":"mllm"}],"next_cursor":"100"}